CBF Papers Tracker

Control Barrier Function papers | Updated: 2026-07-27 00:02 UTC

GitHub Repository Update Workflow Project README Issues More Repositories

No papers match current filters.

MPC/Planning114 citations2023-03-01Paper ->

A Survey on the Control Lyapunov Function and Control Barrier Function for Nonlinear-Affine Control Systems

Boqian Li, Shiping Wen, Zheng Yan, G. Wen, Tingwen Huang

This survey provides a brief overview on the control Lyapunov function (CLF) and control barrier function (CBF) for general nonlinear-affine control systems. The problem of control is formulated as an optimization problem where the optimal control policy is derived by solving a constrained quadratic programming (QP) problem. The CLF and CBF respectively characterize the stability objective and the safety objective for the nonlinear control systems. These objectives imply important properties including controllability, convergence, and robustness of control problems. Under this framework, optimal control corresponds to the minimal solution to a constrained QP problem. When uncertainties are explicitly considered, the setting of the CLF and CBF is proposed to study the input-to-state stability and input-to-state safety and to analyze the effect of disturbances. The recent theoretic progress and novel applications of CLF and CBF are systematically reviewed and discussed in this paper. Finally, we provide research directions that are significant for the advance of knowledge in this area.

Robotics0 citations2022-09-18arXiv ->

Dynamic Control Barrier Function-based Model Predictive Control to Safety-Critical Obstacle-Avoidance of Mobile Robot

Zhu Jian, Zihong Yan, Xuanang Lei, Zih-Rong Lu, Bin Lan et al.

This paper presents an efficient and safe method to avoid static and dynamic obstacles based on LiDAR. First, point cloud is used to generate a real-time local grid map for obstacle detection. Then, obstacles are clustered by DBSCAN algorithm and enclosed with minimum bounding ellipses (MBEs). In addition, data association is conducted to match each MBE with the obstacle in the current frame. Considering MBE as an observation, Kalman filter (KF) is used to estimate and predict the motion state of the obstacle. In this way, the trajectory of each obstacle in the forward time domain can be parameterized as a set of ellipses. Due to the uncertainty of the MBE, the semi-major and semi-minor axes of the parameterized ellipse are extended to ensure safety. We extend the traditional Control Barrier Function (CBF) and propose Dynamic Control Barrier Function (D-CBF). We combine D-CBF with Model Predictive Control (MPC) to implement safety-critical dynamic obstacle avoidance. Experiments in simulated and real scenarios are conducted to verify the effectiveness of our algorithm. The source code is released for the reference of the community11Code: https://github.com/jianzhuozhuTHU/MPC-D-CBF..

Robotics108 citations2022-05-17Paper ->

Discrete-Time Control Barrier Function: High-Order Case and Adaptive Case

Y. Xiong, Dihua Zhai, M. Tavakoli, Yuanqing Xia

This article proposes the novel concepts of the high-order discrete-time control barrier function (CBF) and adaptive discrete-time CBF. The high-order discrete-time CBF is used to guarantee forward invariance of a safe set for discrete-time systems of high relative degree. An optimization problem is then established unifying high-order discrete-time CBFs with discrete-time control Lyapunov functions to yield a safe controller. To improve the feasibility of such optimization problems, the adaptive discrete-time CBF is designed, which can relax constraints on system control input through time-varying penalty functions. The effectiveness of the proposed methods in dealing with high relative degree constraints and improving feasibility is verified on the discrete-time system of a three-link manipulator.

Robotics0 citations2021-09-25arXiv ->

Safety-Critical Control and Planning for Obstacle Avoidance between Polytopes with Control Barrier Functions

A. Thirugnanam, Jun Zeng, K. Sreenath

Obstacle avoidance between polytopes is a chal-lenging topic for optimal control and optimization-based tra-jectory planning problems. Existing work either solves this problem through mixed-integer optimization, relying on simpli-fication of system dynamics, or through model predictive control with dual variables using distance constraints, requiring long horizons for obstacle avoidance. In either case, the solution can only be applied as an offline planning algorithm. In this paper, we exploit the property that a smaller horizon is sufficient for obstacle avoidance by using discrete-time control barrier function (DCBF) constraints and we propose a novel optimization formulation with dual variables based on DCBFs to generate a collision-free dynamically-feasible trajectory. The proposed optimization formulation has lower computational complexity compared to existing work and can be used as a fast online algorithm for control and planning for general nonlinear dynamical systems. We validate our algorithm on different robot shapes using numerical simulations with a kinematic bicycle model, resulting in successful navigation through maze environments with polytopic obstacles.

Robotics526 citations2021-08-18Paper ->

High-Order Control Barrier Functions

Wei Xiao, C. Belta

We approach the problem of stabilizing a dynamical system while optimizing a cost and satisfying safety constraints and control limitations. For (nonlinear) affine control systems and quadratic costs, it has been shown that control barrier functions (CBFs) guaranteeing safety and control Lyapunov functions (CLFs) enforcing convergence can be used to (conservatively) reduce the optimal control problem to a sequence of quadratic programs (QPs). Existing works in this category have two main limitations. First, with one exception, they are based on the assumption that the relative degree of the system with respect to a function enforcing a safety constraint is one. Second, the QPs can easily become infeasible, in particular for problems with many safety constraints and tight control limitations. We propose high-order CBFs (HOCBFs), which can accommodate systems of arbitrary relative degrees. For each safety constraint, by using Lyapunov-like conditions, we construct a set of controls that renders the intersection of a set of sets forward invariant, which implies the satisfaction of the original constraint. We formulate optimal control problems with constraints given by HOCBF and CLF, and propose two methods—the penalty method and the parameterization method—to address the feasibility problem. Finally, we show how our methodology can be extended for safe navigation in unknown environments with long-term feasibility. We illustrate the proposed framework on adaptive cruise control and robot control problems.

MPC/Planning0 citations2021-04-06arXiv ->

Robust Control Barrier–Value Functions for Safety-Critical Control

Jason J. Choi, Donggun Lee, K. Sreenath, C. Tomlin, Sylvia L. Herbert

This paper works towards unifying two popular approaches in the safety control community: Hamilton-Jacobi (HJ) reachability and Control Barrier Functions (CBFs). HJ Reachability has methods for direct construction of value functions that provide safety guarantees and safe controllers, however the online implementation can be overly conservative and/or rely on chattering bang-bang control. The CBF community has methods for safe-guarding controllers in the form of point-wise optimization using quadratic programs (CBF-QP), where the CBF-based safety certificate is used as a constraint. However, finding a valid CBF for a general dynamical system is challenging. This paper unifies these two methods by introducing a new reachability formulation inspired by the structure of CBFs to construct a Control Barrier-Value Function (CBVF). We verify that CBVF is a viscosity solution to a novel Hamilton-Jacobi-Isaacs Variational Inequality and preserves the same safety guarantee as the original reachability formulation. Finally, inspired by the CBF-QP, we propose a QP-based online control synthesis for systems affine in control and disturbance, whose solution is always the CBVF’s optimal control signal robust to bounded disturbance. We demonstrate the benefit of using the CBVFs for double-integrator and Dubins car systems by comparing it to previous methods.

Robotics180 citations2021-01-01Paper ->

Guaranteed Obstacle Avoidance for Multi-Robot Operations With Limited Actuation: A Control Barrier Function Approach

Yuxiao Chen, Andrew W. Singletary, A. Ames

This letter considers the problem of obstacle avoidance for multiple robotic agents moving in an environment with obstacles. A decentralized supervisory controller is synthesized based on control barrier functions (CBF) that guarantees obstacle avoidance with limited actuation capability. The proposed method is applicable to general nonlinear robot dynamics and is scalable to an arbitrary number of agents. Agent-to-agent communication is not required, yet a simple broadcasting scheme improves the performance of the algorithm. The key idea is based on a control barrier function constructed with a backup controller, and we show that by assuming other agents respecting the same CBF condition, the supervisory control algorithm can be implemented decentrally and guarantees obstacle avoidance for all agents.

MPC/Planning244 citations2020-08-11Paper ->

Safe reinforcement learning: A control barrier function optimization approach

Z. Marvi, Bahare Kiumarsi

This article presents a learning‐based barrier certified method to learn safe optimal controllers that guarantee operation of safety‐critical systems within their safe regions while providing an optimal performance. The cost function that encodes the designer's objectives is augmented with a control barrier function (CBF) to ensure safety and optimality. A damping coefficient is incorporated into the CBF which specifies the trade‐off between safety and optimality. The proposed formulation provides a look‐ahead and proactive safety planning and results in a smooth transition of states within the feasible set. That is, instead of applying an optimal controller and intervening with it only if the safety constraints are violated, the safety is planned and optimized along with the performance to minimize the intervention with the optimal controller. It is shown that addition of the CBF into the cost function does not affect the stability and optimality of the designed controller within the safe region. This formulation enables us to find the optimal safe solution iteratively. An off‐policy reinforcement learning (RL) algorithm is then employed to find a safe optimal policy without requiring the complete knowledge about the system dynamics, while satisfies the safety constraints. The efficacy of the proposed safe RL control design approach is demonstrated on the lane keeping as an automotive control problem.

Robotics0 citations2020-07-22arXiv ->

Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Function

Jun Zeng, Bike Zhang, K. Sreenath

The optimal performance of robotic systems is usually achieved near the limit of state and input bounds. Model predictive control (MPC) is a prevalent strategy to handle these operational constraints, however, safety still remains an open challenge for MPC as it needs to guarantee that the system stays within an invariant set. In order to obtain safe optimal performance in the context of set invariance, we present a safety-critical model predictive control strategy utilizing discrete-time control barrier functions (CBFs), which guarantees system safety and accomplishes optimal performance via model predictive control. We analyze the feasibility and the stability properties of our control design. We verify the properties of our method on a 2D double integrator model for obstacle avoidance. We also validate the algorithm numerically using a competitive car racing example, where the ego car is able to overtake other racing cars.

MPC/Planning0 citations2020-03-17arXiv ->

Control Barrier Function-Based Quadratic Programs Introduce Undesirable Asymptotically Stable Equilibria

Matheus F. Reis, Antonio Pedro Aguiar, P. Tabuada

Control Lyapunov functions (CLFs) and control barrier functions (CBFs) have been used to develop provably safe controllers by means of quadratic programs (QPs), guaranteeing safety in the form of trajectory invariance with respect to a given set. In this letter, we show that this framework can introduce equilibrium points (particularly at the boundary of the safe set) other than the minimum of the Lyapunov function into the closed-loop system. We derive explicit conditions under which these undesired equilibria (which can even appear in the simple case of linear systems with just one convex unsafe set) are asymptotically stable. To address this issue, we propose an extension to the QP-based controller unifying CLFs and CBFs such that the resulting system trajectories avoid the undesirable equilibria problem on the boundary of the safe set. The solution is illustrated in the design of a collision-free controller.

MPC/Planning0 citations2019-09-10arXiv ->

A Barrier Function Approach to Finite-Time Stochastic System Verification and Control

Cesar Santoyo, Maxence Dutreix, Samuel D. Coogan

This paper studies the problem of enforcing safety of a stochastic dynamical system over a finite-time horizon. We use stochastic control barrier functions as a means to quantify the probability that a system exits a given safe region of the state space in finite time. A barrier certificate condition that bounds the expected value of the barrier function over the time horizon is recast as a sum-of-squares optimization problem for efficient numerical computation. Unlike prior works, the proposed certificate condition includes a state-dependent upper bound on the evolution of the expectation. We present formulations for both continuous-time and discrete-time systems. Moreover, for systems for which the drift dynamics are affine-in-control, we propose a method for synthesizing polynomial state feedback controllers that achieve a specified probability of safety. Several case studies are presented which benchmark and illustrate the performance of our verification and control method in the continuous-time and discrete-time domains.

MPC/Planning2673 citations2016-09-21arXiv ->

Control Barrier Function Based Quadratic Programs for Safety Critical Systems

A. Ames, Xiangru Xu, J. Grizzle, P. Tabuada

Safety critical systems involve the tight coupling between potentially conflicting control objectives and safety constraints. As a means of creating a formal framework for controlling systems of this form, and with a view toward automotive applications, this paper develops a methodology that allows safety conditions—expressed as control barrier functions—to be unified with performance objectives—expressed as control Lyapunov functions—in the context of real-time optimization-based controllers. Safety conditions are specified in terms of forward invariance of a set, and are verified via two novel generalizations of barrier functions; in each case, the existence of a barrier function satisfying Lyapunov-like conditions implies forward invariance of the set, and the relationship between these two classes of barrier functions is characterized. In addition, each of these formulations yields a notion of control barrier function (CBF), providing inequality constraints in the control input that, when satisfied, again imply forward invariance of the set. Through these constructions, CBFs can naturally be unified with control Lyapunov functions (CLFs) in the context of a quadratic program (QP); this allows for the achievement of control objectives (represented by CLFs) subject to conditions on the admissible states of the system (represented by CBFs). The mediation of safety and performance through a QP is demonstrated on adaptive cruise control and lane keeping, two automotive control problems that present both safety and performance considerations coupled with actuator bounds.

Robotics239 citations2015-07-01Paper ->

Control barrier function based quadratic programs with application to bipedal robotic walking

Shao-Chen Hsu, Xiangru Xu, A. Ames

Learning1062 citations2014-12-01Paper ->

Control barrier function based quadratic programs with application to adaptive cruise control

A. Ames, J. Grizzle, P. Tabuada

MPC/Planning0 citations2026-07-23arXiv ->

Robust Adaptive Backup Control Barrier Functions

Ersin Daş, David E. J. van Wijk, Tamas G. Molnar, Aaron D. Ames, Joel W. Burdick

We propose a notion of robust adaptive backup control barrier functions for nonlinear control affine systems with parametric uncertainty in both the drift dynamics and actuation matrix. Backup control barrier functions guarantee safety by predicting the system's trajectory under a pre-certified safe controller. However, these predictions rely on the model and can be inaccurate when the system contains unknown parameters. To address this issue, we estimate the unknown parameters using element-wise certified adaptive estimators that provide a parameter adaptation law and component-wise estimation error bounds. We compute the backup flow using the estimated model and tighten the safety conditions using these certified bounds. The resulting safety conditions account for the sensitivity of the predicted flow to parameter estimation errors. Moreover, to handle uncertainty in the actuation matrix, we use a duality-based reformulation that enables the use of a computationally efficient quadratic-program-based safety filter. We prove that controllers satisfying the proposed robust adaptive backup control barrier function constraints guarantee safety under parametric uncertainty and input constraints.

MPC/Planning0 citations2026-07-22arXiv ->

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

Robotics0 citations2026-07-22arXiv ->

Safe and Scalable Multi-Drone Payload Transport via CBF-based Reinforcement Learning with Zero-Shot Sim-to-Real Transfer

Jaeyoun Choi, Oswin So, Songyuan Zhang, Cooper Taylor, Chuchu Fan

Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster response. However, the complex coupled dynamics among drones, cables, and payloads pose significant challenges, and existing approaches remain limited in safety and scalability, particularly in dynamic and unstructured environments. In this work, we propose a learning-based framework for safe and scalable multi-drone cooperative payload transport. We introduce a minimal 2D abstraction that preserves the task-relevant drone-payload coupling required for coordination and safety, while remaining computationally efficient for large-scale learning. Using domain randomization over team size and physical parameters, we train a fully distributed policy via Discrete Graph Control Barrier Function Proximal Policy Optimization (DGPPO), enabling robust zero-shot sim-to-real transfer without fine-tuning. Extensive real-world evaluations demonstrate that a single learned policy generalizes across varying team sizes and task scenarios. Furthermore, multi-group hardware experiments show that the same policy can safely operate in dynamic environments, where other drone teams act as moving obstacles. These results indicate that the proposed framework enables efficient, safe, and scalable multi-drone payload transportation with strong generalization to complex real-world conditions.

Robotics0 citations2026-07-22arXiv ->

Distributed Motion Planning with Safety Guarantees for Self-Reconfiguring Robotic Boats

Alejandro Gonzalez-Garcia, Wei Wang, Wei Xiao, Wilm Decre, Jan Swevers et al.

Aquatic self-reconfigurable robots must assemble into desired shapes while ensuring safe interactions among multiple agents. This paper proposes a hybrid framework that combines distributed Model Predictive Control (MPC) with Control Barrier Functions (CBFs) for multi-agent shape formation and reconfiguration. Given a desired shape and target assignment, a distributed MPC scheme, solved via the Alternating Direction Method of Multipliers (ADMM), computes coordinated trajectories through local optimization and information exchange. To ensure safety in real time, distributed CBF-based filters are applied to enforce inter-agent collision avoidance. The proposed approach leverages the predictive capabilities of MPC to mitigate local minima, while CBFs provide formal safety guarantees despite the nonconvexity of the underlying optimization problem. Simulation results with up to 25 agents and experimental validation with four physical robots demonstrate the effectiveness and scalability of the framework.

Robotics0 citations2026-07-21arXiv ->

Learning Personalized Safety Interventions for Haptic Human-Robot Shared Control

Dawei Zhang, Roberto Tron

Haptic feedback provides an implicit channel for communicating safety intentions during human-robot shared control. Existing haptic guidance systems typically employ predefined intervention strategies that cannot accommodate the diverse safety preferences of individual users or application scenarios. To address this limitation, we propose a Learning from Haptics (LfH) framework that learns user-preferred safety interventions from sparse demonstrations, eliminating the need for manual trial-and-error design. Our framework is built on a differentiable Control Barrier Function (CBF)-based optimization layer that automatically adjusts the underlying safety parameters to match the demonstrated haptic responses. Instead of tuning controller parameters directly, users teach the system how they expect it to intervene during teleoperation. The resulting haptic guidance reflects the demonstrated intervention preferences while preserving the intuitive interaction of haptic shared control. Simulation and hardware experiments demonstrate that the proposed framework can learn personalized safety interventions from sparse user input and reduce the mismatch between the generated haptic feedback and the demonstrated preferences.

MPC/Planning0 citations2026-07-21arXiv ->

Pose-Parameterized Motion Planning and CBF-QP Self-Collision Filtering for a Long-Reach Drilling Boom

Mehdi Heydari Shahna, Tuomo Kivelä, Jouni Mattila

Long-reach drilling booms must reach successive poses without self-collision. Moving from operator-supervised control toward autonomy requires collision-aware motion planning and execution. For the Sandvik SB60, this study adapts established methods by integrating pose-parameterized planning with a capsule-based control barrier function quadratic program (CBF-QP) in measured-state inverse kinematics (IK). A fixed task-specific parameter set within each task generates waypoints, detours, timed references, and chained motion without target-specific retuning. The offline detour planner screens candidate waypoints using 23 selected rod-segment-to-body-region distances, whereas the online CBF-QP filters joint velocities using 14 configured capsule-pair constraints from a nine-primitive whole-body capsule model. Evaluation considers two drilling tasks in a manufacturer-developed SB60 Simscape Multibody model: a five-target restricted-orientation tour and a three-target full-pose tour. Across several hundred thousand samples, the method produced zero IK failures, generated several detour waypoints, achieved millimetre-level mean final-position error, and recorded no sampled CBF margins below the reported thresholds.

Theory0 citations2026-07-19arXiv ->

Optimal Safety Control using High-Order Control Barrier Functions

Neng Li, Zuodong Pan, Jiaxing Wang, Weiguo Xia, Wei Ren

This paper investigates the optimal safety control problem of nonlinear control systems by proposing novel high-order control barrier functions (HOCBFs). Different from zeroing HOCBFs, two novel HOCBFs are derived and the safety controllers are designed in an explicit way. Next, we implement vector Lyapunov function approach to propose a novel high-order control Lyapunov function (HOCLF) for the stabilization control problem. The relations between the proposed and existing HOCBFs are discussed. Afterwards, the compatibility of the proposed HOCLF and HOCBF is addressed to guarantee the stabilization and safety control objectives simultaneously, and thus the optimal controller is established. Finally, a numerical example from the navigation problem of quadrotors is presented to illustrate the efficacy of the derived results.

Robotics0 citations2026-07-18arXiv ->

ADMM-Based Safety-Critical Distributed NMPC for Cooperative Transportation by Quadrupedal Robots

Ruturaj S. Sambhus, Kapi Ketan Mehta, Yicheng Zeng, Kaveh Akbari Hamed

This paper presents a safety-critical distributed nonlinear model predictive control (DNMPC) framework for cooperative payload transportation by teams of quadrupedal robots. The proposed approach models the robotic team and the shared payload as a dynamically coupled networked system with rigid holonomic coupling constraints arising from cooperative transportation. To enable distributed real-time optimization, the centralized finite-horizon optimal control problem is decomposed into parallel local NMPC subproblems coordinated through the alternating direction method of multipliers (ADMM). The resulting distributed framework enforces consensus over both payload-state and interaction-wrench trajectories while explicitly incorporating acceleration-level holonomic coupling constraints within the distributed predictive control formulation. Safety-critical obstacle avoidance constraints for both the robotic agents and payload are enforced using higher-order control barrier functions (HOCBFs). The framework is validated through numerical simulations with teams of two, three, and four quadrupedal robots transporting shared payloads in cluttered environments. Real-time experiments on two- and three-robot teams demonstrate safe and robust transportation under payload uncertainty and external disturbances. Compared with centralized NMPC, the proposed framework achieves up to 23% reduction in average NLP solve time while maintaining comparable closed-loop performance. Ablation studies further demonstrate robustness to communication delays and show that explicit payload-state consensus and holonomic constraints substantially improve payload tracking and distributed coordination over existing wrench-only consensus formulations.

Robotics0 citations2026-07-18arXiv ->

AI-Augmented Model Predictive Control for Safe and Adaptive Rendezvous and Proximity Operations

Luca Sportelli, Tyler Barr, Cagri Kilic, Di Wu

Autonomous rendezvous and proximity operations (RPO) in adversarial orbital environments require guidance architectures balancing target pursuit, safety preservation, and real-time adaptability under dynamically evolving interaction conditions. Although learning-based approaches show promise, their application to safety-critical orbital robotics remains limited by concerns regarding interpretability, robustness, and constraint awareness. This work presents an adaptive Model Predictive Control (MPC) framework for autonomous spacecraft RPO in multi-agent adversarial scenarios. The proposed architecture combines a constrained receding-horizon MPC formulation with a data-driven supervisory tuning layer that adjusts controller parameters from offline closed-loop evaluation and online interaction geometry. Relative motion follows Clohessy-Wiltshire (CW) dynamics, enabling computationally efficient finite-horizon prediction and real-time quadratic optimization. The MPC formulation incorporates actuator limits, predictive keep-out-zone constraints, slack-variable feasibility handling, and optional Control Barrier Function (CBF) safety filtering. Rather than generating thrust commands directly, the adaptive layer modifies interpretable MPC parameters, including tracking weights, safety penalties, minimum-separation objectives, and keep-out-zone objectives. The framework was evaluated in the official Kerbal Space Program Differential Game (KSPDG) Capture-the-Satellite environment through Monte Carlo simulations. Results demonstrate improved closed-loop robustness, adaptive maneuvering behavior, and rendezvous performance compared with fixed-parameter MPC while preserving safety-aware operation and real-time feasibility, providing a modular, interpretable foundation for adaptive spacecraft RPO.

Robotics0 citations2026-07-17arXiv ->

Certifiable Safe Model-Based Reinforcement Learning with Control-Affine Dynamics Approximation

Hao Zhou, Yanze Zhang, Cameron Reid, Wenhao Luo

Safe model-based reinforcement learning (RL) often bridges control-theoretic analysis and RL for robots to safely explore (partially) unknown system dynamics while deriving control actions for task efficiency. The control performance and safety assurance typically rely on prior knowledge of partially modeled nominal system dynamics and the data-driven models that compensate for residual model uncertainties. However, existing methods often overlook the structure of residual model uncertainties (e.g., components affine in control), which could lead to overly conservative robot behaviors or invalid safety guarantees under the safe learning-based controllers. This paper proposes a safe reinforcement learning framework that learns control-affine dynamics with a certifiable data-driven safe policy using control barrier functions (CBF). Specifically, we first use Control-Affine Random Fourier Features (ARFF) to model robot dynamics in a control-affine form, which offers computational efficiency that scales with dataset size and reduces potential model bias for model-based reinforcement learning. Then, a model-free, efficient uncertainty quantification method using adaptive conformal prediction (ACP) is applied to quantify the uncertainty in the safety constraint arising from the learned control-affine dynamics. This allows for data-driven safety assurance amenable to principled and efficient controller synthesis with CBF. Simulation results on the cartpole and the 3D quadrotor platforms demonstrate the effectiveness of the proposed framework.

Robotics0 citations2026-07-17arXiv ->

Dynamic Constraint Reconstruction Based Control Barrier Functions for Safety-Critical Control of High-Dimensional Manipulators

Bingsheng Zhang, Shen Wang, Qiang Wang, Muguo Du, Donghai Shi et al.

Control barrier functions (CBFs) provide formal safety guarantees for constrained nonlinear systems, but their effectiveness relies on accurate system dynamics. In high-dimensional manipulators subject to unknown disturbances and model uncertainties, fixed safety constraints constructed from nominal dynamics may become inconsistent with the actual system behavior, leading to safety degradation or excessive conservatism. This paper proposes a dynamic constraint reconstruction based control barrier function (DCR-CBF) framework for safety-critical control of disturbed robotic manipulators. An extended state observer is employed to estimate lumped disturbances online, and the estimated disturbance is incorporated into high-order control barrier functions to reconstruct safety constraints according to the estimated true dynamics. To address estimation inaccuracies, a safety margin is introduced, and a sufficient condition is derived to guarantee forward invariance under bounded estimation errors. Simulation studies on a 4-DOF excavation manipulator demonstrate that the proposed DCR-CBF method achieves zero safety violation under strong unknown disturbances while significantly improving trajectory-tracking performance compared with standard and robust CBF methods.

Robotics0 citations2026-07-16arXiv ->

Risk-Aware Belief Control Barrier Functions over Random Finite Sets

Shaohang Han, Gang Chen, Yixi Cai, Ignacio Torroba, Ivan Stenius et al.

Ensuring robot safety in unknown, dynamic environments is a fundamental requirement. It involves inferring the states of an unknown and time-varying number of moving objects from noisy, incomplete measurements. We address safe control under the induced multi-object state uncertainty with a risk-aware belief control barrier function (BCBF) framework. The uncertainty is captured by a random finite set (RFS) belief, estimated by a sequential Monte Carlo probability hypothesis density (SMC-PHD) filter that represents it with a set of particles. Building directly on these particles, we construct a nonsmooth BCBF, establish forward invariance of the safe set under continuous prediction, and derive an explicit condition under which discrete updates preserve safety. Simulation and real-world underwater experiments demonstrate the effectiveness and efficiency of the proposed approach.

Robotics0 citations2026-07-16arXiv ->

Safe Execution of RL Policies Via Acceleration-Based CBF-QP Constraint Enforcement for Real-World Robotic Deployments

Bastien Muraccioli, Alice Cariou, Pierre-Alexandre Leziart, Mathieu Celerier, Arnaud Demont et al.

Reinforcement Learning (RL) has demonstrated remarkable capabilities for solving complex robotic control problems, but its lack of safety guarantees severely limits deployment on hardware. In particular, as legged robots and manipulators often operate near safety-critical boundaries, out-of-distribution states can lead to failure upon deployment. To address this, we introduce Acc-CBF-QP, an acceleration-based Quadratic Program (QP) safety filter using Control Barrier Functions (CBFs) that constrains any RL policy onto a safe set at runtime without modifying training. The method applies to unconstrained and Safe-RL policies, and enforces joint position, velocity, torque, and collision constraints within a unified optimization framework. A key contribution is the formulation of RL+QP tasks that regulate deviation from the RL command when constraints would otherwise be violated. We introduce a TorqueTask, minimizing torque deviation, and a Forward Dynamics Task, minimizing induced acceleration deviation, thus providing principled control over safety-performance trade-offs. Experiments on a 7-DoF Kinova Gen3 manipulator and a 19-DoF Unitree H1 humanoid, both in simulation and on hardware, highlight substantial reductions in constraint violations. On the real H1 hardware, a Safe-RL policy alone yielded 10.04 violations/s, which were reduced by 92% to 0.80 violations/s when augmented with Acc-CBF-QP. On the Kinova Gen3, Acc-CBF-QP fully eliminated violations. Nominal task performance of the RL objective is preserved in violation-free regimes. Under aggressive velocity commands on H1, Acc-CBF-QP improves execution by preventing constraint-induced shutdowns, yielding longer survival times. The full pipeline is open-source.

MPC/Planning0 citations2026-07-15arXiv ->

Discriminative Barrier Functions for Safe Adversarial Imitation Learning from Observation

Anubhav Vishwakarma, Bhaumik Mehta, Caleb Hsu, Byron Boots, Karen Leung et al.

Inverse Reinforcement Learning (IRL) algorithms are powerful tools for learning from and generalizing expert demonstrations, but they often rely on unconstrained exploration, rendering them unsafe for real-world deployment. Meanwhile, Control Barrier Functions (CBFs) can guarantee the safety of control systems, but the analytical design of CBFs can be time-consuming and esoteric. In this work, we address these limitations jointly by constraining reward function candidacy during IRL to the space of CBFs, yielding a formulation that exhibits safe online control with continuous experiential improvement. Crucially, this framework enables the data-driven recovery of barrier functions directly from unlabeled expert observations. We demonstrate that the recovered barrier function is robust to unsafe states entirely absent from the expert data. Furthermore, we benchmark our method against standard IRL baselines in a simulated navigation environment, demonstrating improved safety performance. Finally, we investigate the trade-offs of planning-based versus policy-based IRL methods across both simulation and a real world obstacle avoidance task.

Robotics0 citations2026-07-15arXiv ->

Safe Overtaking for Autonomous Racing Using Hierarchical Optimization and Learning-Based Control

Hassan Jardali, Kai Yin, Lantao Liu

Autonomous racing overtaking requires balancing competitive performance with safety under nonlinear vehicle dynamics and real-time constraints. Model Predictive Control (MPC) combined with Control Barrier Functions (CBFs) provides a principled mechanism for certifying forward invariance of a safe set. However, commonly used fixed-decay discrete-time CBF formulations can become overly conservative in interactive racing scenarios, limiting overtaking performance and requiring manual tuning across track conditions. This paper proposes a hierarchical overtaking framework that explicitly separates maneuver-level decision making from safety-certified trajectory control, reducing conservatism while preserving safety. A high-level Mixed-Integer Quadratic Program (MIQP) resolves the combinatorial passing-side selection problem by selecting a feasible overtaking topology, while a nonlinear Frenet-frame MPC enforces vehicle dynamics and safety through embedded discrete-time CBF constraints. This decomposition isolates the combinatorial complexity of maneuver selection from the continuous trajectory optimization. To further mitigate the sensitivity of fixed-decay barrier constraints, a reinforcement learning policy adapts the discrete-time CBF decay parameter online, enabling context-dependent modulation of safety margins without directly controlling vehicle inputs. Simulation and scaled-hardware experiments show that no single fixed decay parameter achieves uniformly strong performance across tracks, whereas the adaptive strategy attains the highest aggregate success rate and consistently strong safety--performance trade-offs without per-track tuning, improving robustness to environment variation while maintaining safety constraint satisfaction in nominal operation.

Robotics0 citations2026-07-14arXiv ->

Autonomous Tracking and Terminal Guidance of Moving Targets for Fixed-Wing UAVs

Wei-Hao Liou, Teng-Hu Cheng

This study introduces a unified control framework for fixed-wing unmanned aerial vehicles (UAVs) fitted with a pan-tilt (PT) camera, intended to perform an end-to-end mission spanning from initial target detection to accurate terminal engagement. The proposed system employs a three-phase strategy: a vision-based target acquisition phase, an NMPC-based tracking phase, and a terminal guidance phase. During tracking, the framework uses an Unscented Kalman Filter (UKF) to fuse YOLO-based visual detections with inertial measurements, enabling robust target state estimation under unknown dynamics. To ensure reliable visual contact, we introduce a constraint-aware Nonlinear Model Predictive Control (NMPC) strategy that incorporates Control Barrier Functions (CBFs) to explicitly prevent UAV self-occlusion -- a common limitation in fixed-wing tracking. Upon satisfying terminal engagement conditions, the system seamlessly transitions control to a quaternion-based Biased Proportional Navigation Guidance (BPNG) law, enforcing precise impact angle constraints. High-fidelity simulations demonstrate that the framework achieves stable, robust tracking and accurate terminal interception while strictly respecting the vehicle's dynamic limits and camera field-of-view constraints.

Robotics0 citations2026-07-14arXiv ->

Model-Based Diffusion Optimal Control for Multi-Robot Motion Planning

Zhilin He, Yorai Shaoul, Jiaoyang Li

Multi-Robot Motion Planning in continuous environments, where robots must generate dynamically feasible, collision-free trajectories, is challenging due to the combinatorial growth of the joint trajectory space and the difficulty of enforcing dynamic feasibility and hard safety constraints. Recent approaches recast trajectory planning as probabilistic inference, sampling from a posterior over trajectories using diffusion models whose score functions are learned from demonstration data. While showing promising performance, these approaches are limited: they often rely on sizable demonstration datasets and struggle to rigorously enforce dynamics and hard safety constraints during sampling. To this end, we introduce Model-Based Diffusion Optimal Control (MDOC), a model-based diffusion planner that efficiently produces dynamically feasible trajectories without relying on data. Crucially, we show that MDOC's safety mechanism -- combining known dynamics models with Control Barrier Function-constrained projections -- naturally scales to multi-robot planning settings through Conflict-Based Search. Across simulation experiments, this integrated method consistently outperforms representative baseline planners in sample efficiency, geometric smoothness, and success rate, while reducing computation time and producing collision-free trajectories.

Robotics0 citations2026-07-12arXiv ->

D-SafeMPC: Diffusion-Driven Safe Model Predictive Control with Discrete-Time Control Barrier Functions

Erdi Sayar, Ersin Daş, Joel W. Burdick, Alois Knoll, Erdal Kayacan

A key limitation on the use of diffusion models in robotic planning is their inability to inherently enforce safety or dynamical constraints, which often results in physically infeasible or unsafe outputs. Hybrid approaches that employ model predictive control (MPC) to address this problem can be unstable, as poor trajectory initializations from the diffusion model prevent the MPC from converging to a safe and feasible solution. To overcome these challenges, we propose D-SafeMPC, which enhances the interaction between diffusion and control. Our method guides the reverse diffusion process with control barrier functions (CBFs) and control Lyapunov functions (CLFs) and employs an iterative-projection scheme where an MPC refines the trajectory at each denoising step. This steers sampling toward safe, goal-directed regions and provides reliable MPC warm starts. In simulations on a Franka manipulator across four scenarios (one static-obstacle and three dynamic-obstacle settings) and in a sim-to-real experiment on a physical Franka robot, D-SafeMPC improves safety, task success rates, and planning efficiency over state-of-the-art baselines. To facilitate reproducibility, our source code and experimental configurations are available in a repository at https://github.com/erdiphd/D-SafeMPC

Learning0 citations2026-07-10arXiv ->

Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation

Alex Zongo, Peng Wei

Learning-based separation assurance for small Unmanned Aircraft Systems (sUAS) achieves near-zero collision rates in simulation, but assumes accurate position and velocity information from Global Navigation Satellite Systems (GNSS). This assumption fails in urban environments, where multipath propagation, signal blockage, and intentional interference degrade navigation integrity. This raises a fundamental architectural question for deploying learned separation policies under GNSS degradation: should runtime safety mechanisms filter the policy's actions or its observations? This work evaluates both approaches for multi-agent sUAS separation under adversarial GNSS degradation. Both architectures first estimate a worst-case traffic state consistent with bounded observation uncertainty, then diverge: action filtering constrains policy outputs via discrete-time control barrier functions evaluated at the worst-case state, while observation filtering presents the worst-case state directly to the policy as corrected input. Experimental results show that action filtering provides negligible safety improvement, while observation filtering reduces near mid-air collisions by 90% and remains robust to the barrier function's tradeoff between separation distance and closing rate. These results suggest that, for policies with learned safety behaviors, preserving the policy's decision authority outperforms overriding its actions with hand-designed constraints.

Robotics0 citations2026-07-10arXiv ->

SEAMLiS: Visibility-Aware Safety for Perception-Limited Multi-Robot Exploration

Taekyung Kim, Rahul H Kumar, Aswin D. Menon, Tzu-Hsiang Lin, Dimitra Panagou

Autonomous exploration in unknown environments is typically driven by informative frontiers, viewpoints, or trajectories, while local safety controllers avoid obstacles represented in the current map. Under finite sensing range and limited field of view, this separation can be unsafe: an exploration stack may plan optimistically through unobserved space and steer the sensor toward information gain rather than along the direction of motion, causing hidden obstacles to be detected too late for bounded-actuation avoidance. This paper presents SEAMLiS (Safe Exploration for Autonomous Multi-Robot Systems Under Limited Sensing), a modular execution-layer safety framework for decentralized multi-robot exploration. SEAMLiS preserves the upstream exploration stack, including the goal allocator and local planner, and enforces safety at the execution layer through perception-aware attitude and positional filters. A gatekeeper-based attitude filter switches between a visibility-promoting yaw policy and a velocity-tracking backup policy to preserve visibility of the critical known-free/unknown boundary with sufficient braking margin. A Control Barrier Function (CBF)-based positional filter then avoids known obstacles, newly detected obstacles, and other robots. We provide sufficient collision-avoidance conditions and validate the framework in randomized simulation, Isaac Sim, and Crazyflie hardware experiments. Results show collision-free exploration across tested single- and multi-robot settings while retaining much of the efficiency of visibility-promoting yaw control.

Robotics0 citations2026-07-09arXiv ->

SplatCtrl: Perception-Action Coupling via Gaussian Scene Representations and Reactive Robot Control

Siddarth Jain, Ho Jin Choi

Robotic manipulators excel in structured environments but face substantial challenges in unstructured and dynamic settings. This paper presents SplatCtrl, a unified framework for real-time scene reconstruction and reactive robot motion generation to enable collision-free robotic arm control in previously unseen and continuously changing environments. Building on 3D Gaussian Splatting (3D-GS), we introduce a hybrid voxel-based filtering and dynamic Gaussian relocation strategy that supports efficient scene reconstruction from RGB-D streams while accommodating environmental changes. For safe and reactive control, we further propose a method for deriving continuous signed distance functions from isotropic Gaussians, providing stable and differentiable collision probability estimates that bridge classical distance fields with the modern implicit representation. These continuous distance metrics are incorporated into control barrier functions, resulting in a unified perception-action coupling framework that supports smooth and reliable real-time motion generation in response to scene changes. Experimental validation in simulation, on physical robot, and within shared human-robot workspace demonstrates the framework's effectiveness, achieving integrated scene reconstruction and reactive control in uncertain, and dynamic environments.

MPC/Planning0 citations2026-07-02arXiv ->

Reference-Governed Distributed Safe Gradient Flow for Safe Optimal Output Agreement of Multi-Agent Systems

Zhanglin Shangguan, Wei Xiao, Bo Yang, Xinping Guan

This paper studies safe optimal output agreement for nonlinear multi-agent systems with output safety constraints. Existing safe feedback optimization methods often implement gradient-flow dynamics directly through the plant input, which may require high-order control barrier functions (HOCBFs). The resulting derivative-chain design is tuning-sensitive and can introduce additional equilibrium conditions that alter the steady-state optimal solution. We propose a reference-governed two-layer architecture that separates lower-layer output regulation from upper-layer distributed optimization. The upper layer filters the reference gradient flow through first-order control barrier function constraints, which are easier to tune and preserve the steady-state optimality structure of the original agreement problem. The lower layer uses an internal-model-based output regulator with a reference-dependent Lyapunov function, from which dynamic safety margins (DSMs) are constructed to certify transient output safety. We prove forward invariance, optimal-solution preservation under DSM-compatibility conditions, and convergence via a Lyapunov small-gain argument. Simulations validate safe convergence, show advantages over HOCBF-based feedback optimization, and demonstrate adaptive tangential objective shaping for escaping spurious equilibria induced by nonconvex obstacles.

Robotics0 citations2026-07-01arXiv ->

Robust Operational Space Control with Conformal Disturbance Bounds for Safe Redundant Manipulation

Wenhua Liu, Fan Zhang, Qin Lin

Redundant robotic manipulators operating in constrained and human-interactive environments require accurate task-space tracking together with rigorous safety guarantees under dynamic uncertainties. Classical operational space computed torque controller (OSCTC) relies on accurate dynamic models and degrades in the presence of disturbances. In contrast, the data-driven paradigm of residual learning approximates disturbances as functions learned from full-state measurements, which are often noisy in practice, lack rigorous theoretical guarantees, and introduce additional design complexity. This paper proposes a robust OSCTC framework that integrates an extended state observer (ESO) with conformal prediction to combine model-based robustness and data-driven adaptability. The ESO estimates lumped disturbances directly in operational space without requiring full-state measurements as in residual learning, and a robust control barrier function (CBF) is constructed to enforce safety under uncertainty. However, robust CBFs require a known disturbance-variation bound to guarantee absolute safety, which often leads to conservatism in practice. To address this limitation, we further employ a sliding-window conformal prediction mechanism to estimate the bound online in a distribution-free manner, thereby achieving practical probabilistic safety guarantees. Experiments on a 7-DoF Franka Research 3 manipulator demonstrate millimeter-level tracking accuracy and real-time safe control at 1~kHz under various disturbances.

MPC/Planning0 citations2026-06-24arXiv ->

Control Barrier Function only Formation Tracking in Multi-Agent Systems

S. Saharsh, Pushpak Jagtap

This paper presents a real-time control framework for formation tracking of heterogeneous multi-agent systems with non-linear dynamics. The proposed method formulates a single Control Barrier Function-like constraint within a quadratic optimization setting that addresses formation tracking. Relying on the relative information of neighboring agents, the controller is designed to operate without the need for manual parameter tuning or a separate nominal formation controller. The leader-follower framework is validated through simulations of moving formations.

Theory0 citations2026-06-24arXiv ->

Deterministic Non-Smooth Safety via Dual-Algebraic Control Barrier Functions

Mohammadreza Kamaldar

This paper presents a dual-algebraic framework for control barrier functions (CBFs) that guarantees deterministic execution using exclusively elementary arithmetic. We develop this deterministic approach to solve a fundamental bottleneck in safety-critical control: pointwise minima naturally compose intersecting safe sets, but generate non-smooth boundaries where standard Lie derivatives fail. Existing mathematical workarounds inject approximation bias, probabilistic non-determinism, or combinatorial execution delays that strictly impede hard real-time hardware certification. By embedding the system state and vector field into the dual-number ring, our method extracts both the composite barrier value and its exact directional derivative in a single evaluation. The standard floating-point minimum deterministically isolates a single vertex of the Clarke generalized gradient for the quadratic-program solver. We prove this selected vertex constitutes a valid Clarke subgradient and the resulting simultaneous-enforcement safety filter guarantees forward invariance. The arithmetic overhead remains a fixed constant factor, strictly independent of state dimension or constraint count. We extend this framework to arbitrary $\min$/$\max$ Boolean compositions and systems of higher relative degree, validating the computational scaling on three physical examples.

Robotics0 citations2026-06-23arXiv ->

Causality-Based Parametric Control Barrier Function for Safe Multi-Vehicle Interaction

Yiwei Lyu, Caleb Chang, John M. Dolan

Safe control has been widely studied in various safety-critical applications, for instance, autonomous driving. In order to ensure the autonomous vehicle does not collide with other vehicles, it is essential to obtain an accurate expectation of surrounding vehicles' behavior and react adaptively. Instead of assuming fully cooperative and homogeneous vehicles using the same safety-critical controllers, recent works have been exploring different data-driven approaches to model the neighboring vehicles' underlying controllers with observed data. However, existing works either suffer from 1) the inter-vehicle influence during the multi-vehicle interaction, which makes it hard to determine the causality of surrounding vehicles' behavior in controller modeling, or 2) being dominated by the worst-case analysis, which may lead to overly conservative behavior. In this paper, we extend the prior work on Parametric-Control Barrier Function (Parametric-CBF) to multi-robot interactions with embedded causality inference to explicitly reason over the inter-vehicle influence. Given the learned Causality-based Parametric-CBF, we present an adaptive safety-critical controller that allows the ego vehicle to safely react to surrounding vehicles with the learned expectation. We demonstrate that by leveraging the motion flexibility among multi-vehicle systems, task efficiency can be greatly improved in various interaction-intensive scenarios.

Learning0 citations2026-06-20arXiv ->

Decentralized Geometric Control for Cable-Suspended Payload Transport with Adaptive Mass Estimation

Hadi Hajieghrary, Benedikt Walter, Paul Schmitt, Miguel Hurtado

Cooperative aerial transport requires controllers that respect nonlinear manifold geometry, operate without centralized coordination, and respect operational safety constraints. To address these demands, we present GPAC, a four-layer hierarchical architecture that enables $N$ quadrotors to transport a cable-suspended payload without a central coordinator or by exchanging cable states or adaptive parameters. The key insight is implicit coordination: each quadrotor independently estimates its effective load share from local cable measurements, so combined forces converge to the correct total, even without knowledge of $N$ or the payload mass; the payload position is reconstructed locally from each agent's own cable geometry, and the only inter-agent communication is a low-rate neighbor-position broadcast for collision avoidance. GPAC operates directly on the full nonlinear configuration manifold and integrates geometric position and attitude control, anti-swing regulation, an extended-state observer for wind rejection, concurrent learning-based mass estimation without persistent excitation, and a priority-ordered control barrier function (CBF)-inspired safety filter that reduces operational risk, with input-to-state safety (ISSf) margins that hold exactly under single-constraint activation. A compatibility result shows that the filter's force modifications keep the desired attitude within the almost-global stability region of the $\mathrm{SO}(3)$ attitude controller. Finally, high-fidelity simulation with flexible cables, onboard sensor fusion, and wind turbulence -- with all control and estimation loops closed through the estimator -- yields a mean payload-tracking RMSE of 33.8 cm (2.8\% coefficient of variation over 13 seeds) at a low per-agent computational cost.

Theory0 citations2026-06-19arXiv ->

Conflict-Aware Switching for CBF-CLF-Based Multi-Goal Navigation

Rohan Walia, Kevin Leahy

Quadratic programs (QPs) using Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs) are widely used for safe control in reach-and-avoid navigation. However, the inherently conflicting nature of CBF and CLF constraints can lead to performance degradation, including slowdowns and deadlocks. This issue is exacerbated in multi-goal scenarios, where multiple nominal control objectives must be satisfied under shared safety constraints. Existing approaches for preemptive safety are often computationally expensive or overly conservative, while methods that relax or switch between nominal objectives are not well-suited for sequential goal-to-goal navigation. To address these limitations, we propose a conflict-aware switching strategy that detects high-conflict conditions and switches between available nominal control objectives to reduce constraint conflict. We apply this approach to multi-agent, multi-goal reach-and-avoid scenarios under CBF-CLF-QP control. Compared to a baseline sequential goal traversal strategy, our method reduces both completion time and timeout rates, demonstrating improved performance in satisfying all nominal control objectives while respecting safety constraints.

Robotics0 citations2026-06-17arXiv ->

A Mixed-Reality Testbed for Autonomous Vehicles

H. M. Sabbir Ahmad, Ehsan Sabouni, Emrullah Celik, Zean Wan, Damola Ajeyemi et al.

We propose a mixed-reality, hardware-in-the-loop (HIL) testbed for autonomous vehicles that seamlessly integrates a physical testbed of mobile robots with a high-fidelity simulation environment. The virtual simulation enables the creation of diverse, safety-critical driving scenarios to validate state-of-the-art perception, planning, and control algorithms, while augmenting simulations with physical robots equipped with multimodal sensors in photorealistic virtual environments further facilitating rigorous validation. Our testbed also features vehicular connectivity using wireless communication and can accommodate a large number of agents through the combination of physical robots and virtual simulated agents, supporting research on multi-agent systems including Connected and Autonomous Vehicles (CAVs). Finally, we present a safety-guaranteed framework combining perception, planning and a novel online learning-based controller using Control Barrier Functions (CBFs) for CAVs. Experiments using the proposed framework are used to validate and demonstrate the key functionalities and the overall utility of the testbed to bridge the gap between simulation and real-world hardware deployment.

Robotics0 citations2026-06-16arXiv ->

Memory-Efficient Meta-Reinforcement Learning for Adaptive Safety-Critical Control in Adversarial Spacecraft Proximity Operations

Alejandro Posadas-Nava, Richard Linares, Minduli Wijayatunga

Autonomous spacecraft rendezvous and proximity operations (RPO) require controllers that guarantee safety under thrust constraints while minimizing fuel expenditure. Input-constrained control barrier functions (ICCBFs) provide a control method for nonlinear systems with actuation constraints that construct a forward-invariant safe set. Previous work has shown that learning class-$\mathcal{K}$ functions defining the ICCBF recursion via meta reinforcement learning (meta-RL) yields a robust, non-greedy approach to safety-critical control in RPO. This paper extends that framework further by investigating the performance of three recurrent network architectures (Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Selective State Space Model (Mamba)) and two training algorithms (Proximal Policy Optimization (PPO) and Soft Actor Critic (SAC)) to identify the best setup for tuning ICCBF class-K functions via meta-RL. In addition to cooperative test cases, performance is evaluated in the presence of adversarial behavior where the target spacecraft behaves in a way that worsens the safety of the chaser spacecraft. Results indicate that state space models such as Mamba when used with PPO achieve superior task completion, safety, and fuel-savings compared to other architectures, across all cooperative and uncooperative scenarios tested.

MPC/Planning0 citations2026-06-15arXiv ->

An Adjoint-based Neural Regulator for Real-Time Optimal Control with State Constraints

Isaiah A. Agboola, Yuxin Tong, Uduak Inyang-Udoh

This paper introduces a learning-based control framework for real-time constrained optimal control of nonlinear systems with safety guarantees based on the Pontryagin's Minimum Principle. The approach learns a neural co-state (adjoint) policy that encodes optimality through the system Hamiltonian, rather than directly approximating a control law. Feasibility is enforced separately at runtime through an efficient convex projection that incorporates actuator limits and safety constraints expressed as control barrier functions. We refer to this framework as an adjoint-based neural regulator (ANR) as it yields a controller that satisfies constraints while retaining the optimality structure encoded by the learned adjoint. We demonstrate the effectiveness of the proposed framework on nonlinear constrained control tasks using a unicycle model. The ANR achieves performance at par with nonlinear model predictive control at more than two orders of magnitude lower computational cost, while exhibiting near-invariant performance across unseen scenarios, thus, significantly outperforming reinforcement learning methods in out-of-training-distribution regimes.

Robotics0 citations2026-06-15arXiv ->

PolyMerge: Compressing 3D Gaussian Splats with Polytope Coverings for Provably Safe Resource-Constrained Navigation

Jihoon Hong, Chih-Yuan Chiu, Sara Fridovich-Keil, Glen Chou

Obstacle avoidance is essential for safe navigation and motion planning. Recent radiance field reconstruction methods enable object detection and modeling with high fidelity, but remain too memory- and compute-intensive for on-board perception-based path planning. To address these limitations, we propose PolyMerge to convert a large, photorealistic 3D Gaussian Splatting (3DGS) model of a scene into a lightweight representation of convex polytopes whose union provably over-approximates all obstacles in the original 3DGS model. PolyMerge tunes the polytope count to trade off conservativeness and compute cost, and integrates with control barrier functions (CBFs) to plan collision-free paths. We showcase PolyMerge in simulation and hardware experiments on a Crazyflie drone, which uses PolyMerge to compute and follow safe trajectories in real time under severe onboard compute constraints, outperforming baselines in speed while guaranteeing safety. For our code and videos, visit https://athlon76.github.io/PolyMerge-website/.

Theory0 citations2026-06-14arXiv ->

Stability Analysis in Multi-Constraint Safety Filters for Linear Systems

Shima Sadat Mousavi, Pol Mestres, Aaron D. Ames

Multi-constraint safety filters based on control barrier functions for linear systems with affine state constraints yield continuous piecewise-affine closed-loop dynamics and may introduce boundary equilibria and unstable active-set modes. Although they guarantee forward invariance, they can change nominal stability, and it remains unclear when unstable modes cause divergence versus bounded, convergent behavior. This paper develops a geometric framework to separate these cases: leveraging explicit active-set realizations, we show that equilibria associated with nonempty active sets lie on the corresponding constraint faces and that any unstable directions are tangent to those faces due to exponential enforcement of the active constraints. We characterize mode stability via a minimum-phase test, certify divergence under fixed active sets using recession cones, and derive tractable linear-matrix-inequality conditions for global exponential stability or boundedness using Lyapunov and LaSalle arguments.

MPC/Planning0 citations2026-06-13arXiv ->

Robust Conformal CBF and CLF Controllers via Iterative Policy Updates

Omid Mirzaeedodangeh, Eliot Shekhtman, Nikolai Matni, Lars Lindemann

Conformal prediction (CP) has been used to obtain probabilistic bounds on the error between a learned dynamics model and the true but unknown system. Such CP bounds can then be embedded into robust control Lyapunov function (CLF) and control barrier function (CBF) frameworks. However, such an approach does not retain stability/safety guarantees because of the distribution shift between the closed-loop trajectory distribution under the deployed CLF/CBF policy and the trajectory distribution from which the CP bound and its guarantees were derived. To address this issue, we propose an episodic framework that iteratively updates the robust conformal CLF/CBF policy while maintaining stability/safety guarantees across episodes. We achieve this by (1) using adversarially robust conformal prediction, and (2) quantifying a distribution shift budget that allows us to control how much the model error can increase across policy updates. This distribution shift budget is derived via a closed-loop trajectory sensitivity analysis, yielding an implicit and an explicit update rule for the CP bound. We analyze convergence of our algorithm, which we demonstrate on three case studies. To the best of our knowledge, these are the first results that provide stability/safety guarantees for robust conformal CBF/CLF policies.

Robotics0 citations2026-06-12arXiv ->

A Modular Dual-Arm Apple Harvesting Robot with Enhanced Field Performance

Keyi Zhu, Kyle Lammers, Chaaran Arunachalam, Kaixiang Zhang, Renfu Lu et al.

Robotic apple harvesting offers a promising solution to labor shortages in commercial orchards, but low throughput and poor performance in orchard environments hinder its commercial adoption. This paper presents a modular dual-arm apple harvesting robot that uses a vertically stacked arms to enable simultaneous operation in the upper and lower zones of a single tree, simplifying platform positioning from multi-tree lateral repositioning to single-tree stops. Compared to our prior horizontal dual-arm system, the platform integrates 5 advances: (1)a foundation-model-based perception pipeline combining Grounding-DINO and EfficientViT-SAM for robust fruit localization in unstructured outdoor environments; (2)7th-order jerk-bounded trajectory generation paired with a Control Barrier Function safety filter to achieve fast yet safe arm motions; (3)a linear sweep harvesting strategy with a 10cm approach buffer and rotational detachment that improves picking reliability; (4)a temporal-logic-based dual-arm coordination policy with vision-arm async scheduling that maximizes usage of a shared vacuum source; and (5)field validation in 2 commercial orchards covering different apple varieties and tree architectures during the 2025 harvest season. Across the 1738 arm cycles collected in these field trials, the system achieved an 80.0% per-attempt success rate and a mean per-arm cycle time of 7.53s. Fruit damage assessments confirmed that 91.2% of robotically harvested fruit retained the highest USDA grade (Extra Fancy), with bruise rates between 2.4% and 4.9%. With further improvements in the picking cycle time and handling of heavy foliage occlusions, this new modular robot design holds promise for commercial harvesting of apples.

Robotics0 citations2026-06-11arXiv ->

Embedding ISO 10218 Safety Compliance in Robots via Control Barrier Functions for Human-Robot Collaboration

Federico Parma, Cesare Tonola, Nicola Pedrocchi, Manuel Beschi

Human-Robot Collaboration (HRC) requires strict adherence to safety standards, such as ISO 10218, to prevent harmful interactions. Standard Speed and Separation Monitoring (SSM) filters calculate safe robotic speeds based on conservative assumptions, such as constant human velocity, which prevents accurate predictions of minimum separation distances and causes unnecessary operational halts. This paper proposes a Control Barrier Function (CBF) that explicitly incorporates human acceleration data to analytically forward-predict the minimum human-robot separation distance during a worst-case robotic stopping trajectory. To guarantee safety at the control level, this predictive CBF is integrated as an inequality constraint within a Sequential Quadratic Programming (SQP) framework. Specifically, two methods are proposed: Method I, a CBF-constrained PD safety filter; and Method II, a task-scaling SQP controller that enforces a spatial tube constraint. Simulated and real-world experiments on a UR10e robot evaluate the two proposed methods against a standard industrial SSM module baseline. Results demonstrate that Method II dynamically modulates execution speed and confines spatial deviations. Compared to Method I, Method II achieves a 63\% reduction in mean trajectory error and avoids excessive evasive manoeuvres, ensuring high task throughput while complying with ISO 10218 SSM guidelines.

MPC/Planning0 citations2026-06-10arXiv ->

Individual Control Barrier Functions-Guided Diffusion Model for Safe Offline Multi-Agent Reinforcement Learning

Qingyun Guo, Junyi Shi, Jianuo Huang, Tianyu Shi

Offline reinforcement learning allows control policies to be learned directly from data without online interaction, making it suitable for safety-critical tasks. Recent studies have applied diffusion models to offline reinforcement learning to leverage their strong capacity for modeling complex data distributions. However, existing approaches primarily focus on single-agent settings, leaving the safety challenges in multi-agent environments largely unexplored. In this work, we propose a safe offline multi-agent reinforcement learning algorithm that embeds neural individual control barrier functions into the diffusion model to enhance safety during trajectory generation, with control policies recovered through inverse dynamics. We evaluate our algorithm across diverse benchmarks, demonstrating substantial safety improvements while maintaining competitive rewards.

Other0 citations2026-06-10arXiv ->

CBF-based Driving Assistance for Traffic Flow Stabilization

Hayate Irie, Masaki Inoue, Banri Okita, Akira Yamaguchi, Tomohiro Taki et al.

This manuscript addresses a hierarchical control system designed to suppress traffic congestion. The lower-layered controllers, implemented in each controlled vehicle, monitor microscopic vehicle behaviors and assist human drivers to ensure sufficient spacing for following vehicles. This spacing logic is designed based on the Control Barrier Function. Meanwhile, the upper-layered controller monitors the macroscopic traffic flow and activates the necessary lower-layered controllers, using a data-driven approach for the activation logic design. Furthermore, the effectiveness of the proposed control system is evaluated in a traffic flow simulation environment constructed using real-world traffic data.

MPC/Planning0 citations2026-06-08arXiv ->

Who Earns the Safety? Intervention-Aware Quantum Predictive Control with Safety Attribution

Yifan Wang

Hard safety filters are increasingly placed downstream of learned controllers to guarantee constraint satisfaction at run time. Yet a filtered controller that never violates a constraint may still have learned nothing about safety: the filter can silently repair an incompetent upstream policy, so that post-filter success measures the filter, not the policy. We argue that safe policy learning should ask who earns the safety - the policy or its protective layers - and we make this question measurable. We introduce Intervention-Aware Variational Quantum Differentiable Predictive Control (IA-VQC-DPC), which (i) trains a compact variational quantum circuit (VQC) policy under a primal-dual intervention budget that penalizes reliance on a differentiable Control-Barrier-Function (CBF) projection, and (ii) is evaluated with a safety-attribution protocol that decomposes the executed-trajectory correction into a CBF term and a deployment runtime-guard term, and stress-tests the policy with guard-off evaluation. On closed-loop, high-fidelity BOPTEST building-control emulators (5 seeds, 60 episodes per method), intervention-aware training significantly lowers the quantum policy's raw pre-filter violation and total safety-layer reliance (both p < 10^-4) with no significant energy regression; at an equal approximately 400-parameter budget the quantum policy is significantly safer and more comfortable than a matched classical policy. Guard-off evaluation confirms the improvement is policy-level and exposes a valuable negative result: a learned differentiable energy head is only safe when paired with a distribution-aware runtime guard. The attribution protocol is general beyond quantum policies and buildings.

Robotics0 citations2026-06-08arXiv ->

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models

Seongbin Park, Fan Zhang, Baharan Mirzasoleiman, Shahriar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees against collisions with task-irrelevant objects in the scene. Existing safety filters sidestep this problem by querying a vision-language model (VLM) to identify obstacles and their locations. This, however, is too slow to run in the control loop and can only be invoked at episode initialization, leaving the filter unable to track moving obstacles. We discover that a small number of attention heads within a VLA model reliably localize the object the policy intends to approach. These heads can be exploited within a training-free safety framework that obtains the active target from the attention heads at every step, treats the remainder of the scene as obstacles, and feeds these into a Control Barrier Function (CBF) filter. Together with a lightweight real-time object tracker, this allows for collision avoidance for non-static obstacles. We evaluate our framework on SafeLIBERO, which we extend with moving obstacles. On the original static benchmark, our method performs comparably to an oracle that uses privileged simulator state to identify the target, emulating a VLM-based identification step run once at episode initialization. On the dynamic variant, where the oracle's init-time target assignment becomes stale, our method substantially outperforms it by 43%, on average. Our findings suggest that the perceptual signals needed for real-time safety filtering are already present within VLA policies and can be exploited without additional training or heavy auxiliary models.

Robotics0 citations2026-06-08arXiv ->

ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

Fan Zhang, Seongbin Park, Baharan Mirzasoleiman, Shariar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution, yet their generalization capabilities remain fundamentally limited. They3 lack the robustness required to handle perturbations, frequently failing when con-4 fronted with lighting changes, altered camera viewpoints, or small initial-state5 variations. We propose PROBEACT, a training-free runtime intervention frame-6 work that detects and recovers from grasping and placement failures in pre-7 trained VLA policies without modifying their weights or requiring additional8 demonstrations. PROBEACT combines three components: (i) a lightweight multi-9 target hidden-state probe that predicts the 3D positions of task-relevant objects10 from intermediate VLA features, with Hungarian-matched identity tracking for11 multi-object scenes; (ii) an object-agnostic kinematic state machine that detects12 grasp, transport, and placement failures using only gripper-internal signals and13 end-effector kinematics; and (iii) a hierarchical Control Barrier Function (CBF)14 filter that encodes repeated-failure locations as soft safe-set constraints, mini-15 mally correcting VLA actions while preserving baseline behavior. As a plug-and-16 play, training-free intervention loop, PROBEACT is orthogonal to existing train-17 ing pipelines. Evaluated on the LIBERO-plus benchmark, our framework acts as18 a universal safety net, improving the success rate of the OpenVLA-OFT model19 from 69.6% to 74.1%, while demonstrating broad applicability to both base and20 fine-tuned VLA policies.

Robotics0 citations2026-06-08arXiv ->

Safe Polytope-in-Polytope Motion Planning and Control with Control Barrier Functions

Alejandro Gonzalez-Garcia, Dries Dirckx, Jan Swevers, Wilm Decré

Autonomous mobile robots operating in tight environments require motion planning frameworks that account for the physical footprint of the robot. Simplifying the geometry to a point or a circle is conservative and discards information needed to successfully and safely traverse narrow passages. This work proposes a safe local motion planning and control method that guarantees that a polytopic robot footprint stays inside a continuously updated convex free-space region. The containment condition is formulated as a set of discrete-time control barrier function constraints within a model predictive controller. The number of safety constraints depends on the complexity of the local free-space geometry and the robot shape, instead of the number of obstacles. The proposed free-space formulation does not need any obstacle detection or segmentation. A comparative analysis against a polytope-based obstacle avoidance formulation confirms favorable scaling up to a reduction of 91$\times$ in computation time as the number of obstacles increases. The approach is validated in simulation with an autonomous surface vehicle and on hardware with a non-holonomic mobile robot, using both occupancy grids and LiDAR sensing. The experiments demonstrate safe real-time motion planning and control at 10~Hz on an onboard embedded computer, including reactive avoidance of dynamic obstacles.

MPC/Planning0 citations2026-06-06arXiv ->

Exactness Certificates for Closed-Form CBF Safety-Filter Projections

Ankit Goel

For control-affine systems, standard and high-order control barrier function conditions are affine in the control input and are commonly enforced through quadratic-program-based safety filters. Although convex, these optimization problems may be undesirable in embedded, high-rate, or resource-limited implementations. This letter characterizes when the corresponding Euclidean projection can be recovered from the affine inequalities violated by a nominal control input. Given a nominal input, we form the violated set and compute the minimum-norm correction that enforces the violated inequalities with equality. This violated-set correction is closed form, but it need not equal the exact Euclidean projection onto the full feasible set. The main result gives a necessary and sufficient exactness certificate based on primal and dual feasibility, followed by structural sufficient conditions involving interactions among affine-inequality normals. An online certification algorithm is then presented to determine when the closed-form update is exact. When the certificate fails, a finite active-set search can be used to recover the exact projection. Numerical simulations illustrate that the violated-set correction can remain feasible while failing to be the exact projection due to dual infeasibility, and demonstrate computational speedup relative to a standard CBF-QP solver.

MPC/Planning0 citations2026-06-06arXiv ->

A Barrier-Modulated Architecture for Safe Affine Formation Control in Second-Order Multi-Agent Systems

Ashik Abrar Naeem, Mohammad Ariful Haque

Affine formation control offers immense flexibility for coordinating multi-agent maneuvers, but guaranteeing the safety of agents under parametric uncertainties remains an open challenge. This paper proposes a novel safe affine formation control framework for second-order multi-agent systems by integrating Higher-Order Control Barrier Functions (HOCBFs) with Adaptive Dynamic Programming (ADP). We introduce a barrier-modulated control architecture that smoothly attenuates the nominal formation tracking objective when agents approach safety boundaries, preventing conflicting control inputs. Within this architecture, two distinct safety controllers are developed: (1) an analytical barrier-gradient repulsive controller that provides a computationally efficient, rigorous mathematical baseline, and (2) a data-driven optimal safety controller. The data-driven approach utilizes an actor-critic neural network to solve the Hamilton-Jacobi-Bellman (HJB) equation online, enabling optimal collision avoidance even in the presence of unknown system parameters. Using Nagumo's theorem and Lyapunov stability analysis, we formally prove that both controllers guarantee the forward invariance of the safe set ensuring absolute collision avoidance while maintaining Uniformly Ultimately Bounded (UUB) formation tracking errors. Finally, simulations validate the theoretical findings and demonstrate the robustness of the proposed controllers in dynamic obstacle avoidance scenarios.

Robotics0 citations2026-06-05arXiv ->

Verification Framework for the Union of Control Barrier Functions

Chuanrui Jiang, Andrew Clark

Control Barrier Functions (CBFs) have been proposed to ensure safety of autonomous systems. This paper considers control policies that switch between CBF constraints. Under this approach, we represent a complex non-convex safe region as a union of sets that are computationally tractable to verify. We denote this framework as union-CBFs and make the following contributions. First, considering switching CBF-QP controllers, we propose a sufficient condition that ensures (i) the system undergoes a finite number of switches in any finite time interval and ensures (ii) the forward invariance of the closed-loop system in between switches. Second, we consider two types of switching strategies and propose union-CBFs conditions for each strategy to satisfy (i) and (ii). Third, we formulate Sum-of-Squares (SOS) algorithms to verify the conditions. The experiments show that our union-CBFs framework results in a larger safe region compared to high-degree polynomial CBFs. We also show the efficiency of the verification algorithms using a polynomial system model.

Robotics0 citations2026-06-03arXiv ->

A model-free approach to control barrier functions for higher-order systems

Lukas Lanza, Johannes Köhler, Dario Dennstädt, Thomas Berger, Karl Worthmann

Control barrier functions (CBFs) are a widely applied modular tool to ensure safe operation of nonlinear dynamical control systems. However, for their construction accurate knowledge of the system dynamics is typically needed. This requirement was recently alleviated for relative-degree-one systems using techniques from prescribed performance control (PPC) or funnel control (FC). This article extends the model-free CBF design to nonlinear systems of arbitrary relative degree. Moreover, we show with a simple example that a straightforward extension of existing results for relative-degree-one systems fails. Instead, we utilize novel techniques from funnel control to characterize a subset of the controls satisfying a CBF condition without requiring a dynamic model or state measurement. Finally, we demonstrate the applicability of our results on a seven degrees of freedom robotic manipulator with relative degree two.

MPC/Planning0 citations2026-06-01arXiv ->

Power System CBFs

Abdallah Alalem B. Albustami, Ahmad F. Taha, Taylor T. Johnson

Control barrier functions (CBFs) have become a standard tool in safety critical-control systems. CBFs convert state constraints into real time control conditions that certify forward invariance (meaning that once the system starts in a safe region, it remains there for all future times) and minimally modify a nominal controller only when safety is at risk. In power systems, CBF based methods have been proposed for frequency and voltage safety, but they largely remain disconnected from three key features that are central to power system operation: differential algebraic equation (DAE) models that capture network power flow constraints, safety specifications involving algebraic variables such as bus voltages, and formal verification of the resulting closed loop system. This paper closes this gap by developing a CBF framework for power system DAE models that supports safety constraints on both dynamic and algebraic variables. The framework provides real time safety filtering through an optimization layer that wraps around an existing controller and minimally modifies its command to enforce safety. In addition, it provides formal verification (i.e., a mathematical guarantee that all admissible trajectories satisfy the prescribed safety constraints) through an offline reachability based certificate of safe operation. The result is a unified filter and verify methodology for enforcing and certifying frequency and voltage safety in power systems while preserving the DAE structure of the underlying model.

Robotics0 citations2026-06-01arXiv ->

Embedding Semantic Risk into Distance Fields and CBFs for Online Monocular Safe Control

Dawei Zhang, Nuo Chen, Shuo Liu, Roberto Tron, Zhiwen Fan

We propose an online monocular perception-to-control framework that embeds semantic risk into the distance field used by Control Barrier Function (CBF)-based safe navigation and teleoperation. Many perception-based safety filters assign the same distance-based safety margin to all mapped obstacles or use semantics only as a downstream controller adjustment, rather than encoding semantic risk in the spatial representation. Our framework instead reasons online about obstacle geometry and class-dependent risk by embedding semantic information directly into the Euclidean Signed Distance Field (ESDF). This design encodes semantic risk before control optimization, so high-risk objects exert a larger spatial influence in the safety field while retaining efficient ESDF queries at runtime. Specifically, a foundation-model-based SLAM front end reconstructs dense 3-D geometry from monocular RGB video, while per-frame semantic segmentation provides pixel-level class labels that are fused into the reconstructed geometry. The resulting geometric-semantic representation is then converted into an ESDF, where semantic labels identify safety-relevant regions and impose class-dependent inflation before field computation. The semantic-aware ESDF provides the local distance values and spatial derivatives required by the CBF controller, while class-dependent gains further regulate the controller response. Extensive simulation and hardware experiments demonstrate online operation at 10--20 Hz and semantic-aware safe behavior in both teleoperation and autonomous navigation.

  • A. Ames4
  • Wei Xiao3
  • Fan Zhang3
  • K. Sreenath3
  • P. Tabuada3
  • Ersin Daş2
  • Aaron D. Ames2
  • Joel W. Burdick2
  • Alejandro Gonzalez-Garcia2
  • Jan Swevers2
  • Dawei Zhang2
  • Roberto Tron2
  • Seongbin Park4
  • Baharan Mirzasoleiman4
  • Nader Sehatbakhsh4
  • Jun Zeng2
  • Xiangru Xu13
  • J. Grizzle2
  • David E. J. van Wijk3
  • Tamas G. Molnar1
  • Xingjian Li1
  • Kelvin Kan1
  • Deepanshu Verma2
  • Krishna Kumar1
  • Stanley Osher1
  • Samy Wu Fung4
  • Jaeyoun Choi2
  • Oswin So1
  • Songyuan Zhang1
  • Cooper Taylor1
CBF Related Papers
Robotics180 citations2021-01-01Paper ->

Guaranteed Obstacle Avoidance for Multi-Robot Operations With Limited Actuation: A Control Barrier Function Approach

Yuxiao Chen, Andrew W. Singletary, A. Ames

This letter considers the problem of obstacle avoidance for multiple robotic agents moving in an environment with obstacles. A decentralized supervisory controller is synthesized based on control barrier functions (CBF) that guarantees obstacle avoidance with limited actuation capability. The proposed method is applicable to general nonlinear robot dynamics and is scalable to an arbitrary number of agents. Agent-to-agent communication is not required, yet a simple broadcasting scheme improves the performance of the algorithm. The key idea is based on a control barrier function constructed with a backup controller, and we show that by assuming other agents respecting the same CBF condition, the supervisory control algorithm can be implemented decentrally and guarantees obstacle avoidance for all agents.

MPC/Planning2673 citations2016-09-21arXiv ->

Control Barrier Function Based Quadratic Programs for Safety Critical Systems

A. Ames, Xiangru Xu, J. Grizzle, P. Tabuada

Safety critical systems involve the tight coupling between potentially conflicting control objectives and safety constraints. As a means of creating a formal framework for controlling systems of this form, and with a view toward automotive applications, this paper develops a methodology that allows safety conditions—expressed as control barrier functions—to be unified with performance objectives—expressed as control Lyapunov functions—in the context of real-time optimization-based controllers. Safety conditions are specified in terms of forward invariance of a set, and are verified via two novel generalizations of barrier functions; in each case, the existence of a barrier function satisfying Lyapunov-like conditions implies forward invariance of the set, and the relationship between these two classes of barrier functions is characterized. In addition, each of these formulations yields a notion of control barrier function (CBF), providing inequality constraints in the control input that, when satisfied, again imply forward invariance of the set. Through these constructions, CBFs can naturally be unified with control Lyapunov functions (CLFs) in the context of a quadratic program (QP); this allows for the achievement of control objectives (represented by CLFs) subject to conditions on the admissible states of the system (represented by CBFs). The mediation of safety and performance through a QP is demonstrated on adaptive cruise control and lane keeping, two automotive control problems that present both safety and performance considerations coupled with actuator bounds.

Robotics239 citations2015-07-01Paper ->

Control barrier function based quadratic programs with application to bipedal robotic walking

Shao-Chen Hsu, Xiangru Xu, A. Ames

Learning1062 citations2014-12-01Paper ->

Control barrier function based quadratic programs with application to adaptive cruise control

A. Ames, J. Grizzle, P. Tabuada

CBF Related Papers
Robotics0 citations2026-07-22arXiv ->

Distributed Motion Planning with Safety Guarantees for Self-Reconfiguring Robotic Boats

Alejandro Gonzalez-Garcia, Wei Wang, Wei Xiao, Wilm Decre, Jan Swevers et al.

Aquatic self-reconfigurable robots must assemble into desired shapes while ensuring safe interactions among multiple agents. This paper proposes a hybrid framework that combines distributed Model Predictive Control (MPC) with Control Barrier Functions (CBFs) for multi-agent shape formation and reconfiguration. Given a desired shape and target assignment, a distributed MPC scheme, solved via the Alternating Direction Method of Multipliers (ADMM), computes coordinated trajectories through local optimization and information exchange. To ensure safety in real time, distributed CBF-based filters are applied to enforce inter-agent collision avoidance. The proposed approach leverages the predictive capabilities of MPC to mitigate local minima, while CBFs provide formal safety guarantees despite the nonconvexity of the underlying optimization problem. Simulation results with up to 25 agents and experimental validation with four physical robots demonstrate the effectiveness and scalability of the framework.

MPC/Planning0 citations2026-07-02arXiv ->

Reference-Governed Distributed Safe Gradient Flow for Safe Optimal Output Agreement of Multi-Agent Systems

Zhanglin Shangguan, Wei Xiao, Bo Yang, Xinping Guan

This paper studies safe optimal output agreement for nonlinear multi-agent systems with output safety constraints. Existing safe feedback optimization methods often implement gradient-flow dynamics directly through the plant input, which may require high-order control barrier functions (HOCBFs). The resulting derivative-chain design is tuning-sensitive and can introduce additional equilibrium conditions that alter the steady-state optimal solution. We propose a reference-governed two-layer architecture that separates lower-layer output regulation from upper-layer distributed optimization. The upper layer filters the reference gradient flow through first-order control barrier function constraints, which are easier to tune and preserve the steady-state optimality structure of the original agreement problem. The lower layer uses an internal-model-based output regulator with a reference-dependent Lyapunov function, from which dynamic safety margins (DSMs) are constructed to certify transient output safety. We prove forward invariance, optimal-solution preservation under DSM-compatibility conditions, and convergence via a Lyapunov small-gain argument. Simulations validate safe convergence, show advantages over HOCBF-based feedback optimization, and demonstrate adaptive tangential objective shaping for escaping spurious equilibria induced by nonconvex obstacles.

Robotics526 citations2021-08-18Paper ->

High-Order Control Barrier Functions

Wei Xiao, C. Belta

We approach the problem of stabilizing a dynamical system while optimizing a cost and satisfying safety constraints and control limitations. For (nonlinear) affine control systems and quadratic costs, it has been shown that control barrier functions (CBFs) guaranteeing safety and control Lyapunov functions (CLFs) enforcing convergence can be used to (conservatively) reduce the optimal control problem to a sequence of quadratic programs (QPs). Existing works in this category have two main limitations. First, with one exception, they are based on the assumption that the relative degree of the system with respect to a function enforcing a safety constraint is one. Second, the QPs can easily become infeasible, in particular for problems with many safety constraints and tight control limitations. We propose high-order CBFs (HOCBFs), which can accommodate systems of arbitrary relative degrees. For each safety constraint, by using Lyapunov-like conditions, we construct a set of controls that renders the intersection of a set of sets forward invariant, which implies the satisfaction of the original constraint. We formulate optimal control problems with constraints given by HOCBF and CLF, and propose two methods—the penalty method and the parameterization method—to address the feasibility problem. Finally, we show how our methodology can be extended for safe navigation in unknown environments with long-term feasibility. We illustrate the proposed framework on adaptive cruise control and robot control problems.

CBF Related Papers
Robotics0 citations2026-07-01arXiv ->

Robust Operational Space Control with Conformal Disturbance Bounds for Safe Redundant Manipulation

Wenhua Liu, Fan Zhang, Qin Lin

Redundant robotic manipulators operating in constrained and human-interactive environments require accurate task-space tracking together with rigorous safety guarantees under dynamic uncertainties. Classical operational space computed torque controller (OSCTC) relies on accurate dynamic models and degrades in the presence of disturbances. In contrast, the data-driven paradigm of residual learning approximates disturbances as functions learned from full-state measurements, which are often noisy in practice, lack rigorous theoretical guarantees, and introduce additional design complexity. This paper proposes a robust OSCTC framework that integrates an extended state observer (ESO) with conformal prediction to combine model-based robustness and data-driven adaptability. The ESO estimates lumped disturbances directly in operational space without requiring full-state measurements as in residual learning, and a robust control barrier function (CBF) is constructed to enforce safety under uncertainty. However, robust CBFs require a known disturbance-variation bound to guarantee absolute safety, which often leads to conservatism in practice. To address this limitation, we further employ a sliding-window conformal prediction mechanism to estimate the bound online in a distribution-free manner, thereby achieving practical probabilistic safety guarantees. Experiments on a 7-DoF Franka Research 3 manipulator demonstrate millimeter-level tracking accuracy and real-time safe control at 1~kHz under various disturbances.

Robotics0 citations2026-06-08arXiv ->

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models

Seongbin Park, Fan Zhang, Baharan Mirzasoleiman, Shahriar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees against collisions with task-irrelevant objects in the scene. Existing safety filters sidestep this problem by querying a vision-language model (VLM) to identify obstacles and their locations. This, however, is too slow to run in the control loop and can only be invoked at episode initialization, leaving the filter unable to track moving obstacles. We discover that a small number of attention heads within a VLA model reliably localize the object the policy intends to approach. These heads can be exploited within a training-free safety framework that obtains the active target from the attention heads at every step, treats the remainder of the scene as obstacles, and feeds these into a Control Barrier Function (CBF) filter. Together with a lightweight real-time object tracker, this allows for collision avoidance for non-static obstacles. We evaluate our framework on SafeLIBERO, which we extend with moving obstacles. On the original static benchmark, our method performs comparably to an oracle that uses privileged simulator state to identify the target, emulating a VLM-based identification step run once at episode initialization. On the dynamic variant, where the oracle's init-time target assignment becomes stale, our method substantially outperforms it by 43%, on average. Our findings suggest that the perceptual signals needed for real-time safety filtering are already present within VLA policies and can be exploited without additional training or heavy auxiliary models.

Robotics0 citations2026-06-08arXiv ->

ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

Fan Zhang, Seongbin Park, Baharan Mirzasoleiman, Shariar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution, yet their generalization capabilities remain fundamentally limited. They3 lack the robustness required to handle perturbations, frequently failing when con-4 fronted with lighting changes, altered camera viewpoints, or small initial-state5 variations. We propose PROBEACT, a training-free runtime intervention frame-6 work that detects and recovers from grasping and placement failures in pre-7 trained VLA policies without modifying their weights or requiring additional8 demonstrations. PROBEACT combines three components: (i) a lightweight multi-9 target hidden-state probe that predicts the 3D positions of task-relevant objects10 from intermediate VLA features, with Hungarian-matched identity tracking for11 multi-object scenes; (ii) an object-agnostic kinematic state machine that detects12 grasp, transport, and placement failures using only gripper-internal signals and13 end-effector kinematics; and (iii) a hierarchical Control Barrier Function (CBF)14 filter that encodes repeated-failure locations as soft safe-set constraints, mini-15 mally correcting VLA actions while preserving baseline behavior. As a plug-and-16 play, training-free intervention loop, PROBEACT is orthogonal to existing train-17 ing pipelines. Evaluated on the LIBERO-plus benchmark, our framework acts as18 a universal safety net, improving the success rate of the OpenVLA-OFT model19 from 69.6% to 74.1%, while demonstrating broad applicability to both base and20 fine-tuned VLA policies.

CBF Related Papers
Robotics0 citations2021-09-25arXiv ->

Safety-Critical Control and Planning for Obstacle Avoidance between Polytopes with Control Barrier Functions

A. Thirugnanam, Jun Zeng, K. Sreenath

Obstacle avoidance between polytopes is a chal-lenging topic for optimal control and optimization-based tra-jectory planning problems. Existing work either solves this problem through mixed-integer optimization, relying on simpli-fication of system dynamics, or through model predictive control with dual variables using distance constraints, requiring long horizons for obstacle avoidance. In either case, the solution can only be applied as an offline planning algorithm. In this paper, we exploit the property that a smaller horizon is sufficient for obstacle avoidance by using discrete-time control barrier function (DCBF) constraints and we propose a novel optimization formulation with dual variables based on DCBFs to generate a collision-free dynamically-feasible trajectory. The proposed optimization formulation has lower computational complexity compared to existing work and can be used as a fast online algorithm for control and planning for general nonlinear dynamical systems. We validate our algorithm on different robot shapes using numerical simulations with a kinematic bicycle model, resulting in successful navigation through maze environments with polytopic obstacles.

MPC/Planning0 citations2021-04-06arXiv ->

Robust Control Barrier–Value Functions for Safety-Critical Control

Jason J. Choi, Donggun Lee, K. Sreenath, C. Tomlin, Sylvia L. Herbert

This paper works towards unifying two popular approaches in the safety control community: Hamilton-Jacobi (HJ) reachability and Control Barrier Functions (CBFs). HJ Reachability has methods for direct construction of value functions that provide safety guarantees and safe controllers, however the online implementation can be overly conservative and/or rely on chattering bang-bang control. The CBF community has methods for safe-guarding controllers in the form of point-wise optimization using quadratic programs (CBF-QP), where the CBF-based safety certificate is used as a constraint. However, finding a valid CBF for a general dynamical system is challenging. This paper unifies these two methods by introducing a new reachability formulation inspired by the structure of CBFs to construct a Control Barrier-Value Function (CBVF). We verify that CBVF is a viscosity solution to a novel Hamilton-Jacobi-Isaacs Variational Inequality and preserves the same safety guarantee as the original reachability formulation. Finally, inspired by the CBF-QP, we propose a QP-based online control synthesis for systems affine in control and disturbance, whose solution is always the CBVF’s optimal control signal robust to bounded disturbance. We demonstrate the benefit of using the CBVFs for double-integrator and Dubins car systems by comparing it to previous methods.

Robotics0 citations2020-07-22arXiv ->

Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Function

Jun Zeng, Bike Zhang, K. Sreenath

The optimal performance of robotic systems is usually achieved near the limit of state and input bounds. Model predictive control (MPC) is a prevalent strategy to handle these operational constraints, however, safety still remains an open challenge for MPC as it needs to guarantee that the system stays within an invariant set. In order to obtain safe optimal performance in the context of set invariance, we present a safety-critical model predictive control strategy utilizing discrete-time control barrier functions (CBFs), which guarantees system safety and accomplishes optimal performance via model predictive control. We analyze the feasibility and the stability properties of our control design. We verify the properties of our method on a 2D double integrator model for obstacle avoidance. We also validate the algorithm numerically using a competitive car racing example, where the ego car is able to overtake other racing cars.

CBF Related Papers
MPC/Planning0 citations2020-03-17arXiv ->

Control Barrier Function-Based Quadratic Programs Introduce Undesirable Asymptotically Stable Equilibria

Matheus F. Reis, Antonio Pedro Aguiar, P. Tabuada

Control Lyapunov functions (CLFs) and control barrier functions (CBFs) have been used to develop provably safe controllers by means of quadratic programs (QPs), guaranteeing safety in the form of trajectory invariance with respect to a given set. In this letter, we show that this framework can introduce equilibrium points (particularly at the boundary of the safe set) other than the minimum of the Lyapunov function into the closed-loop system. We derive explicit conditions under which these undesired equilibria (which can even appear in the simple case of linear systems with just one convex unsafe set) are asymptotically stable. To address this issue, we propose an extension to the QP-based controller unifying CLFs and CBFs such that the resulting system trajectories avoid the undesirable equilibria problem on the boundary of the safe set. The solution is illustrated in the design of a collision-free controller.

MPC/Planning2673 citations2016-09-21arXiv ->

Control Barrier Function Based Quadratic Programs for Safety Critical Systems

A. Ames, Xiangru Xu, J. Grizzle, P. Tabuada

Safety critical systems involve the tight coupling between potentially conflicting control objectives and safety constraints. As a means of creating a formal framework for controlling systems of this form, and with a view toward automotive applications, this paper develops a methodology that allows safety conditions—expressed as control barrier functions—to be unified with performance objectives—expressed as control Lyapunov functions—in the context of real-time optimization-based controllers. Safety conditions are specified in terms of forward invariance of a set, and are verified via two novel generalizations of barrier functions; in each case, the existence of a barrier function satisfying Lyapunov-like conditions implies forward invariance of the set, and the relationship between these two classes of barrier functions is characterized. In addition, each of these formulations yields a notion of control barrier function (CBF), providing inequality constraints in the control input that, when satisfied, again imply forward invariance of the set. Through these constructions, CBFs can naturally be unified with control Lyapunov functions (CLFs) in the context of a quadratic program (QP); this allows for the achievement of control objectives (represented by CLFs) subject to conditions on the admissible states of the system (represented by CBFs). The mediation of safety and performance through a QP is demonstrated on adaptive cruise control and lane keeping, two automotive control problems that present both safety and performance considerations coupled with actuator bounds.

Learning1062 citations2014-12-01Paper ->

Control barrier function based quadratic programs with application to adaptive cruise control

A. Ames, J. Grizzle, P. Tabuada

CBF Related Papers
MPC/Planning0 citations2026-07-23arXiv ->

Robust Adaptive Backup Control Barrier Functions

Ersin Daş, David E. J. van Wijk, Tamas G. Molnar, Aaron D. Ames, Joel W. Burdick

We propose a notion of robust adaptive backup control barrier functions for nonlinear control affine systems with parametric uncertainty in both the drift dynamics and actuation matrix. Backup control barrier functions guarantee safety by predicting the system's trajectory under a pre-certified safe controller. However, these predictions rely on the model and can be inaccurate when the system contains unknown parameters. To address this issue, we estimate the unknown parameters using element-wise certified adaptive estimators that provide a parameter adaptation law and component-wise estimation error bounds. We compute the backup flow using the estimated model and tighten the safety conditions using these certified bounds. The resulting safety conditions account for the sensitivity of the predicted flow to parameter estimation errors. Moreover, to handle uncertainty in the actuation matrix, we use a duality-based reformulation that enables the use of a computationally efficient quadratic-program-based safety filter. We prove that controllers satisfying the proposed robust adaptive backup control barrier function constraints guarantee safety under parametric uncertainty and input constraints.

Robotics0 citations2026-07-12arXiv ->

D-SafeMPC: Diffusion-Driven Safe Model Predictive Control with Discrete-Time Control Barrier Functions

Erdi Sayar, Ersin Daş, Joel W. Burdick, Alois Knoll, Erdal Kayacan

A key limitation on the use of diffusion models in robotic planning is their inability to inherently enforce safety or dynamical constraints, which often results in physically infeasible or unsafe outputs. Hybrid approaches that employ model predictive control (MPC) to address this problem can be unstable, as poor trajectory initializations from the diffusion model prevent the MPC from converging to a safe and feasible solution. To overcome these challenges, we propose D-SafeMPC, which enhances the interaction between diffusion and control. Our method guides the reverse diffusion process with control barrier functions (CBFs) and control Lyapunov functions (CLFs) and employs an iterative-projection scheme where an MPC refines the trajectory at each denoising step. This steers sampling toward safe, goal-directed regions and provides reliable MPC warm starts. In simulations on a Franka manipulator across four scenarios (one static-obstacle and three dynamic-obstacle settings) and in a sim-to-real experiment on a physical Franka robot, D-SafeMPC improves safety, task success rates, and planning efficiency over state-of-the-art baselines. To facilitate reproducibility, our source code and experimental configurations are available in a repository at https://github.com/erdiphd/D-SafeMPC

CBF Related Papers
MPC/Planning0 citations2026-07-23arXiv ->

Robust Adaptive Backup Control Barrier Functions

Ersin Daş, David E. J. van Wijk, Tamas G. Molnar, Aaron D. Ames, Joel W. Burdick

We propose a notion of robust adaptive backup control barrier functions for nonlinear control affine systems with parametric uncertainty in both the drift dynamics and actuation matrix. Backup control barrier functions guarantee safety by predicting the system's trajectory under a pre-certified safe controller. However, these predictions rely on the model and can be inaccurate when the system contains unknown parameters. To address this issue, we estimate the unknown parameters using element-wise certified adaptive estimators that provide a parameter adaptation law and component-wise estimation error bounds. We compute the backup flow using the estimated model and tighten the safety conditions using these certified bounds. The resulting safety conditions account for the sensitivity of the predicted flow to parameter estimation errors. Moreover, to handle uncertainty in the actuation matrix, we use a duality-based reformulation that enables the use of a computationally efficient quadratic-program-based safety filter. We prove that controllers satisfying the proposed robust adaptive backup control barrier function constraints guarantee safety under parametric uncertainty and input constraints.

Theory0 citations2026-06-14arXiv ->

Stability Analysis in Multi-Constraint Safety Filters for Linear Systems

Shima Sadat Mousavi, Pol Mestres, Aaron D. Ames

Multi-constraint safety filters based on control barrier functions for linear systems with affine state constraints yield continuous piecewise-affine closed-loop dynamics and may introduce boundary equilibria and unstable active-set modes. Although they guarantee forward invariance, they can change nominal stability, and it remains unclear when unstable modes cause divergence versus bounded, convergent behavior. This paper develops a geometric framework to separate these cases: leveraging explicit active-set realizations, we show that equilibria associated with nonempty active sets lie on the corresponding constraint faces and that any unstable directions are tangent to those faces due to exponential enforcement of the active constraints. We characterize mode stability via a minimum-phase test, certify divergence under fixed active sets using recession cones, and derive tractable linear-matrix-inequality conditions for global exponential stability or boundedness using Lyapunov and LaSalle arguments.

CBF Related Papers
MPC/Planning0 citations2026-07-23arXiv ->

Robust Adaptive Backup Control Barrier Functions

Ersin Daş, David E. J. van Wijk, Tamas G. Molnar, Aaron D. Ames, Joel W. Burdick

We propose a notion of robust adaptive backup control barrier functions for nonlinear control affine systems with parametric uncertainty in both the drift dynamics and actuation matrix. Backup control barrier functions guarantee safety by predicting the system's trajectory under a pre-certified safe controller. However, these predictions rely on the model and can be inaccurate when the system contains unknown parameters. To address this issue, we estimate the unknown parameters using element-wise certified adaptive estimators that provide a parameter adaptation law and component-wise estimation error bounds. We compute the backup flow using the estimated model and tighten the safety conditions using these certified bounds. The resulting safety conditions account for the sensitivity of the predicted flow to parameter estimation errors. Moreover, to handle uncertainty in the actuation matrix, we use a duality-based reformulation that enables the use of a computationally efficient quadratic-program-based safety filter. We prove that controllers satisfying the proposed robust adaptive backup control barrier function constraints guarantee safety under parametric uncertainty and input constraints.

Robotics0 citations2026-07-12arXiv ->

D-SafeMPC: Diffusion-Driven Safe Model Predictive Control with Discrete-Time Control Barrier Functions

Erdi Sayar, Ersin Daş, Joel W. Burdick, Alois Knoll, Erdal Kayacan

A key limitation on the use of diffusion models in robotic planning is their inability to inherently enforce safety or dynamical constraints, which often results in physically infeasible or unsafe outputs. Hybrid approaches that employ model predictive control (MPC) to address this problem can be unstable, as poor trajectory initializations from the diffusion model prevent the MPC from converging to a safe and feasible solution. To overcome these challenges, we propose D-SafeMPC, which enhances the interaction between diffusion and control. Our method guides the reverse diffusion process with control barrier functions (CBFs) and control Lyapunov functions (CLFs) and employs an iterative-projection scheme where an MPC refines the trajectory at each denoising step. This steers sampling toward safe, goal-directed regions and provides reliable MPC warm starts. In simulations on a Franka manipulator across four scenarios (one static-obstacle and three dynamic-obstacle settings) and in a sim-to-real experiment on a physical Franka robot, D-SafeMPC improves safety, task success rates, and planning efficiency over state-of-the-art baselines. To facilitate reproducibility, our source code and experimental configurations are available in a repository at https://github.com/erdiphd/D-SafeMPC

CBF Related Papers
Robotics0 citations2026-07-22arXiv ->

Distributed Motion Planning with Safety Guarantees for Self-Reconfiguring Robotic Boats

Alejandro Gonzalez-Garcia, Wei Wang, Wei Xiao, Wilm Decre, Jan Swevers et al.

Aquatic self-reconfigurable robots must assemble into desired shapes while ensuring safe interactions among multiple agents. This paper proposes a hybrid framework that combines distributed Model Predictive Control (MPC) with Control Barrier Functions (CBFs) for multi-agent shape formation and reconfiguration. Given a desired shape and target assignment, a distributed MPC scheme, solved via the Alternating Direction Method of Multipliers (ADMM), computes coordinated trajectories through local optimization and information exchange. To ensure safety in real time, distributed CBF-based filters are applied to enforce inter-agent collision avoidance. The proposed approach leverages the predictive capabilities of MPC to mitigate local minima, while CBFs provide formal safety guarantees despite the nonconvexity of the underlying optimization problem. Simulation results with up to 25 agents and experimental validation with four physical robots demonstrate the effectiveness and scalability of the framework.

Robotics0 citations2026-06-08arXiv ->

Safe Polytope-in-Polytope Motion Planning and Control with Control Barrier Functions

Alejandro Gonzalez-Garcia, Dries Dirckx, Jan Swevers, Wilm Decré

Autonomous mobile robots operating in tight environments require motion planning frameworks that account for the physical footprint of the robot. Simplifying the geometry to a point or a circle is conservative and discards information needed to successfully and safely traverse narrow passages. This work proposes a safe local motion planning and control method that guarantees that a polytopic robot footprint stays inside a continuously updated convex free-space region. The containment condition is formulated as a set of discrete-time control barrier function constraints within a model predictive controller. The number of safety constraints depends on the complexity of the local free-space geometry and the robot shape, instead of the number of obstacles. The proposed free-space formulation does not need any obstacle detection or segmentation. A comparative analysis against a polytope-based obstacle avoidance formulation confirms favorable scaling up to a reduction of 91$\times$ in computation time as the number of obstacles increases. The approach is validated in simulation with an autonomous surface vehicle and on hardware with a non-holonomic mobile robot, using both occupancy grids and LiDAR sensing. The experiments demonstrate safe real-time motion planning and control at 10~Hz on an onboard embedded computer, including reactive avoidance of dynamic obstacles.

CBF Related Papers
Robotics0 citations2026-07-22arXiv ->

Distributed Motion Planning with Safety Guarantees for Self-Reconfiguring Robotic Boats

Alejandro Gonzalez-Garcia, Wei Wang, Wei Xiao, Wilm Decre, Jan Swevers et al.

Aquatic self-reconfigurable robots must assemble into desired shapes while ensuring safe interactions among multiple agents. This paper proposes a hybrid framework that combines distributed Model Predictive Control (MPC) with Control Barrier Functions (CBFs) for multi-agent shape formation and reconfiguration. Given a desired shape and target assignment, a distributed MPC scheme, solved via the Alternating Direction Method of Multipliers (ADMM), computes coordinated trajectories through local optimization and information exchange. To ensure safety in real time, distributed CBF-based filters are applied to enforce inter-agent collision avoidance. The proposed approach leverages the predictive capabilities of MPC to mitigate local minima, while CBFs provide formal safety guarantees despite the nonconvexity of the underlying optimization problem. Simulation results with up to 25 agents and experimental validation with four physical robots demonstrate the effectiveness and scalability of the framework.

Robotics0 citations2026-06-08arXiv ->

Safe Polytope-in-Polytope Motion Planning and Control with Control Barrier Functions

Alejandro Gonzalez-Garcia, Dries Dirckx, Jan Swevers, Wilm Decré

Autonomous mobile robots operating in tight environments require motion planning frameworks that account for the physical footprint of the robot. Simplifying the geometry to a point or a circle is conservative and discards information needed to successfully and safely traverse narrow passages. This work proposes a safe local motion planning and control method that guarantees that a polytopic robot footprint stays inside a continuously updated convex free-space region. The containment condition is formulated as a set of discrete-time control barrier function constraints within a model predictive controller. The number of safety constraints depends on the complexity of the local free-space geometry and the robot shape, instead of the number of obstacles. The proposed free-space formulation does not need any obstacle detection or segmentation. A comparative analysis against a polytope-based obstacle avoidance formulation confirms favorable scaling up to a reduction of 91$\times$ in computation time as the number of obstacles increases. The approach is validated in simulation with an autonomous surface vehicle and on hardware with a non-holonomic mobile robot, using both occupancy grids and LiDAR sensing. The experiments demonstrate safe real-time motion planning and control at 10~Hz on an onboard embedded computer, including reactive avoidance of dynamic obstacles.

CBF Related Papers
Robotics0 citations2026-07-21arXiv ->

Learning Personalized Safety Interventions for Haptic Human-Robot Shared Control

Dawei Zhang, Roberto Tron

Haptic feedback provides an implicit channel for communicating safety intentions during human-robot shared control. Existing haptic guidance systems typically employ predefined intervention strategies that cannot accommodate the diverse safety preferences of individual users or application scenarios. To address this limitation, we propose a Learning from Haptics (LfH) framework that learns user-preferred safety interventions from sparse demonstrations, eliminating the need for manual trial-and-error design. Our framework is built on a differentiable Control Barrier Function (CBF)-based optimization layer that automatically adjusts the underlying safety parameters to match the demonstrated haptic responses. Instead of tuning controller parameters directly, users teach the system how they expect it to intervene during teleoperation. The resulting haptic guidance reflects the demonstrated intervention preferences while preserving the intuitive interaction of haptic shared control. Simulation and hardware experiments demonstrate that the proposed framework can learn personalized safety interventions from sparse user input and reduce the mismatch between the generated haptic feedback and the demonstrated preferences.

Robotics0 citations2026-06-01arXiv ->

Embedding Semantic Risk into Distance Fields and CBFs for Online Monocular Safe Control

Dawei Zhang, Nuo Chen, Shuo Liu, Roberto Tron, Zhiwen Fan

We propose an online monocular perception-to-control framework that embeds semantic risk into the distance field used by Control Barrier Function (CBF)-based safe navigation and teleoperation. Many perception-based safety filters assign the same distance-based safety margin to all mapped obstacles or use semantics only as a downstream controller adjustment, rather than encoding semantic risk in the spatial representation. Our framework instead reasons online about obstacle geometry and class-dependent risk by embedding semantic information directly into the Euclidean Signed Distance Field (ESDF). This design encodes semantic risk before control optimization, so high-risk objects exert a larger spatial influence in the safety field while retaining efficient ESDF queries at runtime. Specifically, a foundation-model-based SLAM front end reconstructs dense 3-D geometry from monocular RGB video, while per-frame semantic segmentation provides pixel-level class labels that are fused into the reconstructed geometry. The resulting geometric-semantic representation is then converted into an ESDF, where semantic labels identify safety-relevant regions and impose class-dependent inflation before field computation. The semantic-aware ESDF provides the local distance values and spatial derivatives required by the CBF controller, while class-dependent gains further regulate the controller response. Extensive simulation and hardware experiments demonstrate online operation at 10--20 Hz and semantic-aware safe behavior in both teleoperation and autonomous navigation.

CBF Related Papers
Robotics0 citations2026-07-21arXiv ->

Learning Personalized Safety Interventions for Haptic Human-Robot Shared Control

Dawei Zhang, Roberto Tron

Haptic feedback provides an implicit channel for communicating safety intentions during human-robot shared control. Existing haptic guidance systems typically employ predefined intervention strategies that cannot accommodate the diverse safety preferences of individual users or application scenarios. To address this limitation, we propose a Learning from Haptics (LfH) framework that learns user-preferred safety interventions from sparse demonstrations, eliminating the need for manual trial-and-error design. Our framework is built on a differentiable Control Barrier Function (CBF)-based optimization layer that automatically adjusts the underlying safety parameters to match the demonstrated haptic responses. Instead of tuning controller parameters directly, users teach the system how they expect it to intervene during teleoperation. The resulting haptic guidance reflects the demonstrated intervention preferences while preserving the intuitive interaction of haptic shared control. Simulation and hardware experiments demonstrate that the proposed framework can learn personalized safety interventions from sparse user input and reduce the mismatch between the generated haptic feedback and the demonstrated preferences.

Robotics0 citations2026-06-01arXiv ->

Embedding Semantic Risk into Distance Fields and CBFs for Online Monocular Safe Control

Dawei Zhang, Nuo Chen, Shuo Liu, Roberto Tron, Zhiwen Fan

We propose an online monocular perception-to-control framework that embeds semantic risk into the distance field used by Control Barrier Function (CBF)-based safe navigation and teleoperation. Many perception-based safety filters assign the same distance-based safety margin to all mapped obstacles or use semantics only as a downstream controller adjustment, rather than encoding semantic risk in the spatial representation. Our framework instead reasons online about obstacle geometry and class-dependent risk by embedding semantic information directly into the Euclidean Signed Distance Field (ESDF). This design encodes semantic risk before control optimization, so high-risk objects exert a larger spatial influence in the safety field while retaining efficient ESDF queries at runtime. Specifically, a foundation-model-based SLAM front end reconstructs dense 3-D geometry from monocular RGB video, while per-frame semantic segmentation provides pixel-level class labels that are fused into the reconstructed geometry. The resulting geometric-semantic representation is then converted into an ESDF, where semantic labels identify safety-relevant regions and impose class-dependent inflation before field computation. The semantic-aware ESDF provides the local distance values and spatial derivatives required by the CBF controller, while class-dependent gains further regulate the controller response. Extensive simulation and hardware experiments demonstrate online operation at 10--20 Hz and semantic-aware safe behavior in both teleoperation and autonomous navigation.

CBF Related Papers
Robotics0 citations2026-06-08arXiv ->

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models

Seongbin Park, Fan Zhang, Baharan Mirzasoleiman, Shahriar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees against collisions with task-irrelevant objects in the scene. Existing safety filters sidestep this problem by querying a vision-language model (VLM) to identify obstacles and their locations. This, however, is too slow to run in the control loop and can only be invoked at episode initialization, leaving the filter unable to track moving obstacles. We discover that a small number of attention heads within a VLA model reliably localize the object the policy intends to approach. These heads can be exploited within a training-free safety framework that obtains the active target from the attention heads at every step, treats the remainder of the scene as obstacles, and feeds these into a Control Barrier Function (CBF) filter. Together with a lightweight real-time object tracker, this allows for collision avoidance for non-static obstacles. We evaluate our framework on SafeLIBERO, which we extend with moving obstacles. On the original static benchmark, our method performs comparably to an oracle that uses privileged simulator state to identify the target, emulating a VLM-based identification step run once at episode initialization. On the dynamic variant, where the oracle's init-time target assignment becomes stale, our method substantially outperforms it by 43%, on average. Our findings suggest that the perceptual signals needed for real-time safety filtering are already present within VLA policies and can be exploited without additional training or heavy auxiliary models.

Robotics0 citations2026-06-08arXiv ->

ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

Fan Zhang, Seongbin Park, Baharan Mirzasoleiman, Shariar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution, yet their generalization capabilities remain fundamentally limited. They3 lack the robustness required to handle perturbations, frequently failing when con-4 fronted with lighting changes, altered camera viewpoints, or small initial-state5 variations. We propose PROBEACT, a training-free runtime intervention frame-6 work that detects and recovers from grasping and placement failures in pre-7 trained VLA policies without modifying their weights or requiring additional8 demonstrations. PROBEACT combines three components: (i) a lightweight multi-9 target hidden-state probe that predicts the 3D positions of task-relevant objects10 from intermediate VLA features, with Hungarian-matched identity tracking for11 multi-object scenes; (ii) an object-agnostic kinematic state machine that detects12 grasp, transport, and placement failures using only gripper-internal signals and13 end-effector kinematics; and (iii) a hierarchical Control Barrier Function (CBF)14 filter that encodes repeated-failure locations as soft safe-set constraints, mini-15 mally correcting VLA actions while preserving baseline behavior. As a plug-and-16 play, training-free intervention loop, PROBEACT is orthogonal to existing train-17 ing pipelines. Evaluated on the LIBERO-plus benchmark, our framework acts as18 a universal safety net, improving the success rate of the OpenVLA-OFT model19 from 69.6% to 74.1%, while demonstrating broad applicability to both base and20 fine-tuned VLA policies.

Robotics0 citations2026-06-08arXiv ->

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models

Seongbin Park, Fan Zhang, Baharan Mirzasoleiman, Shahriar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees against collisions with task-irrelevant objects in the scene. Existing safety filters sidestep this problem by querying a vision-language model (VLM) to identify obstacles and their locations. This, however, is too slow to run in the control loop and can only be invoked at episode initialization, leaving the filter unable to track moving obstacles. We discover that a small number of attention heads within a VLA model reliably localize the object the policy intends to approach. These heads can be exploited within a training-free safety framework that obtains the active target from the attention heads at every step, treats the remainder of the scene as obstacles, and feeds these into a Control Barrier Function (CBF) filter. Together with a lightweight real-time object tracker, this allows for collision avoidance for non-static obstacles. We evaluate our framework on SafeLIBERO, which we extend with moving obstacles. On the original static benchmark, our method performs comparably to an oracle that uses privileged simulator state to identify the target, emulating a VLM-based identification step run once at episode initialization. On the dynamic variant, where the oracle's init-time target assignment becomes stale, our method substantially outperforms it by 43%, on average. Our findings suggest that the perceptual signals needed for real-time safety filtering are already present within VLA policies and can be exploited without additional training or heavy auxiliary models.

Robotics0 citations2026-06-08arXiv ->

ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

Fan Zhang, Seongbin Park, Baharan Mirzasoleiman, S. Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution, yet their generalization capabilities remain fundamentally limited. They3 lack the robustness required to handle perturbations, frequently failing when con-4 fronted with lighting changes, altered camera viewpoints, or small initial-state5 variations. We propose PROBEACT, a training-free runtime intervention frame-6 work that detects and recovers from grasping and placement failures in pre-7 trained VLA policies without modifying their weights or requiring additional8 demonstrations. PROBEACT combines three components: (i) a lightweight multi-9 target hidden-state probe that predicts the 3D positions of task-relevant objects10 from intermediate VLA features, with Hungarian-matched identity tracking for11 multi-object scenes; (ii) an object-agnostic kinematic state machine that detects12 grasp, transport, and placement failures using only gripper-internal signals and13 end-effector kinematics; and (iii) a hierarchical Control Barrier Function (CBF)14 filter that encodes repeated-failure locations as soft safe-set constraints, mini-15 mally correcting VLA actions while preserving baseline behavior. As a plug-and-16 play, training-free intervention loop, PROBEACT is orthogonal to existing train-17 ing pipelines. Evaluated on the LIBERO-plus benchmark, our framework acts as18 a universal safety net, improving the success rate of the OpenVLA-OFT model19 from 69.6% to 74.1%, while demonstrating broad applicability to both base and20 fine-tuned VLA policies.

Non-CBF Papers
Other2 citationsPaper ->

Uncertainty oriented pattern extracting and analyzing via sliding window control

Seungwan Park, Doyoung Kim, Seongbin Park, Unil Yun

Other0 citations2026-07-10Paper ->

Seminal Plasma Microbiome Composition and Its Association with Sperm Morphology in Breeding Boars

Notsile H. Dlamini, S. L. Kameni, Peixin Fan, Seongbin Park, Shengfa F. Liao et al.

Semen quality is a key determinant of reproductive performance in breeding boars, and emerging evidence suggests the seminal microbiome may influence sperm function. However, the composition of the seminal plasma microbiome and its relationship to sperm quality remain poorly characterized. This study aimed to investigate the microbial composition of boar seminal plasma and its association with sperm quality. Semen ejaculates collected from Duroc boars were analyzed and classified as Passed (≥70% normal morphology) or Failed (<70% normal morphology). Seminal plasma was isolated by centrifugation and analyzed using 16S/ITS rRNA gene sequencing. The dominant bacterial phyla were Firmicutes, Bacteroidetes, Proteobacteria, and Actinobacteria. The most abundant genera included Porphyromonas, Bacteroides, and Cladosporium. Only the Shannon diversity index was significantly higher in Failed samples for the bacterial microbiome (p = 0.038). Furthermore, correlation analysis showed a negative association between Tenericutes and sperm concentration (r = −0.90; p = 0.014). Linear discriminant analysis identified microbial biomarkers associated with sperm quality, including Rhodococcus, Sphingomonas, Lactobacillus, Streptococcus, and Empedobacter. The increased abundance of these genera in Failed samples suggests disruption of the normal seminal microbial community. In conclusion, boar seminal plasma harbors a distinct bacterial and fungal microbiome that is associated with sperm morphology.

Other1 citations2026-05-28Paper ->

Agentic Artificial Intelligence for the Automated Generation of Accurate Summary Podcasts of Radiology Research Papers

J. Lee, Kyowon Gu, Jaeseung Shin, J. Min, J. Hwang et al.

Objective To evaluate whether a custom agentic artificial intelligence (AI) pipeline can overcome the limitations of general-purpose large language model tools, when compared with a generic commercial tool (Google NotebookLM [NBLM]), for generating podcast-style summaries of radiology research articles. Materials and Methods Twenty-two PDF-format original research articles published in the April 2025 issue of Radiology were processed using our Programmable, Phoneme-Aware PDF-to-Podcast Pipeline (P5) and NBLM to generate 44 audio episodes. P5 utilizes a multi-agent workflow for script generation, quality assurance, pronunciation enhancement, and audio synthesis. Four radiologists from a pool of 25 (7 generalists and 18 specialists) were randomly assigned to evaluate each blinded audio episode, yielding 176 total evaluations. The primary outcomes were the number of hallucinations (factual errors) per episode and the percentage of hallucination-free episodes. Secondary outcomes included the number of inappropriate statements, mispronunciations, and flow disruptions; the composite quality score (Quality Assessment of Educational Podcasts [QAEP]); the key results coverage score; and overall listener preference. Data were analyzed using generalized linear mixed models. Results The P5 method produced significantly fewer hallucinations per episode compared with NBLM (mean, 0.32 vs. 0.93; P < 0.001) and a higher proportion of hallucination-free episodes (71.6% [63/88] vs. 56.8% [50/88]; P = 0.013), consistently across generalists and specialists. P5 demonstrated significantly fewer mispronunciations (mean, 0.11 vs. 1.62; P < 0.001) and flow disruptions (mean, 0.19 vs. 1.06; P < 0.001) per episode, as well as higher mean QAEP composite scores (4.62 vs. 4.28; P < 0.001), compared with NBLM, consistently across generalists and specialists. Raters preferred P5 over NBLM in 72.7% (64/88) of comparisons (P = 0.003). Conclusion Our custom agentic AI pipeline generated podcast-style summaries of radiology research articles with significantly higher quality and greater listener preference than the generic commercial tool.

Learning1 citations2026-05-01Paper ->

Advanced Temporal Fuzzy Utility Pattern Analysis for Dynamic Uncertain Data Streams

Doyoung Kim, Seongbin Park, Junyoung Park, Hanju Kim, Myungha Cho et al.

High temporal fuzzy utility pattern analysis extracts patterns by considering temporal factors at which items appear, as well as expressing patterns in a linguistic way that humans can easily understand based on the fuzzy theory. However, in real-world stream data environments, data often involve inherent uncertainty, such as inaccuracies in sensor data. Nevertheless, previous studies utilizing the temporal aspect for pattern analysis and fuzzy set theory do not explicitly account for such uncertainty or inaccuracies. Motivated by the limitation, we introduce a scalable method to extract high temporal fuzzy utility patterns within dynamic uncertain data streams. By incorporating uncertainty associated with items appearing in each transaction, our method extracts uncertainty-based high temporal fuzzy utility patterns that more accurately reflect real-world conditions. The pattern expansion process is conducted efficiently with a list structure and various pruning methods. Experimental results indicate the proposed approach exhibits superior performance on runtime and memory usage compared to previous methods under diverse membership functions. Moreover, our method exhibits the highest scalability for increasing data volumes and maintains stable sensitivity to threshold variation while exhibiting the completeness and significance of extracted results. Evaluations under various uncertainty distributions show the superior performance of our approach, and effectiveness evaluations indicate contributions of proposed components. The case study involving the concept-drifting evaluation indicates the applicability of our approach in various real-world environments with better performance.

Other0 citations2026-04-18arXiv ->

Exact Subquadratic Algorithm for Many-to-Many Matching on Planar Point Sets with Integer Coordinates

Seongbin Park, Eunjin Oh

In this paper, we study the many-to-many matching problem on planar point sets with integer coordinates: Given two disjoint sets $R,B \subset [\Delta]^2$ with $|R|+|B|=n$, the goal is to select a set of edges between $R$ and $B$ so that every point is incident to at least one edge and the total Euclidean length is minimized. In the general case that $R$ and $B$ are point sets in the plane, the best-known algorithm for the many-to-many matching problem takes $\tilde{O}(n^2)$ time. We present an exact $\tilde{O}(n^{1.5} \log \Delta)$ time algorithm for point sets in $[\Delta]^2$. To the best of our knowledge, this is the first subquadratic exact algorithm for planar many-to-many matching under bounded integer coordinates.

Learning0 citations2026-04-02arXiv ->

NEMESIS: Noise-suppressed Efficient MAE with Enhanced Superpatch Integration Strategy

Kyeonghun Kim, Hye-Won Jung, Youngung Han, Hyunsu Go, Eun-Won Choi et al.

Volumetric CT imaging is essential for clinical diagnosis, yet annotating 3D volumes is expensive and time-consuming, motivating self-supervised learning (SSL) from unlabeled data. However, applying SSL to 3D CT remains challenging due to the high memory cost of full-volume transformers and the anisotropic spatial structure of CT data, which is not well captured by conventional masking strategies. We propose NEMESIS, a masked autoencoder (MAE) framework that operates on local 128x128x128 superpatches, enabling memory-efficient training while preserving anatomical detail. NEMESIS introduces three key components: (i) noise-enhanced reconstruction as a pretext task, (ii) Masked Anatomical Transformer Blocks (MATB) that perform dual-masking through parallel plane-wise and axis-wise token removal, and (iii) NEMESIS Tokens (NT) for cross-scale context aggregation. On the BTCV multi-organ classification benchmark, NEMESIS with a frozen backbone and a linear classifier achieves a mean AUROC of 0.9633, surpassing fully fine-tuned SuPreM (0.9493) and VoCo (0.9387). Under a low-label regime with only 10% of available annotations, it retains an AUROC of 0.9075, demonstrating strong label efficiency. Furthermore, the superpatch-based design reduces computational cost to 31.0 GFLOPs per forward pass, compared to 985.8 GFLOPs for the full-volume baseline, providing a scalable and robust foundation for 3D medical imaging.

Other0 citations2026-04-01Paper ->

Exploring and detecting utility streams on prelarge and time fading properties

Doyoung Kim, Seongbin Park, Junyoung Park, Hyeonmo Kim, Myungha Cho et al.

Learning0 citations2026-04-01arXiv ->

MATHENA: Mamba-based Architectural Tooth Hierarchical Estimator and Holistic Evaluation Network for Anatomy

Kyeonghun Kim, Jaehyung Park, Young-Tak Han, A. Jung, Seongbin Park et al.

Dental diagnosis from Orthopantomograms (OPGs) requires coordination of tooth detection, caries segmentation (CarSeg), anomaly detection (AD), and dental developmental staging (DDS). We propose Mamba-based Architectural Tooth Hierarchical Estimator and Holistic Evaluation Network for Anatomy (MATHENA), a unified framework leveraging Mamba's linear-complexity State Space Models (SSM) to address all four tasks. MATHENA integrates MATHE, a multi-resolution SSM-driven detector with four-directional Vision State Space (VSS) blocks for O(N) global context modeling, generating per-tooth crops. These crops are processed by HENA, a lightweight Mamba-UNet with a triple-head architecture and Global Context State Token (GCST). In the triple-head architecture, CarSeg is first trained as an upstream task to establish shared representations, which are then frozen and reused for downstream AD fine-tuning and DDS classification via linear probing, enabling stable, efficient learning. We also curate PARTHENON, a benchmark comprising 15,062 annotated instances from ten datasets. MATHENA achieves 93.78% mAP@50 in tooth detection, 90.11% Dice for CarSeg, 88.35% for AD, and 72.40% ACC for DDS.

Other1 citations2026-03-01Paper ->

Flexibility and periodicity intended pattern mining on shifting stream windows in time-series data

Junyoung Park, Doyoung Kim, Seongbin Park, Unil Yun

Learning0 citations2026-01-18arXiv ->

MAESIL: Masked Autoencoder for Enhanced Self-supervised Medical Image Learning

Kyeonghun Kim, Hye-Won Jung, Y. Han, Junsu Lim, Yeonju Jean et al.

Training deep learning models for three-dimensional (3D) medical imaging, such as Computed Tomography (CT), is fundamentally challenged by the scarcity of labeled data. While pre-training on natural images is common, it results in a significant domain shift, limiting performance. Self-Supervised Learning (SSL) on unlabeled medical data has emerged as a powerful solution, but prominent frameworks often fail to exploit the inherent 3D nature of CT scans. These methods typically process 3D scans as a collection of independent 2D slices, an approach that fundamentally discards critical axial coherence and the 3D structural context. To address this limitation, we propose the autoencoder for enhanced self-supervised medical image learning(MAESIL), a novel self-supervised learning framework designed to capture 3D structural information efficiently. The core innovation is the ‘superpatch,’ a 3D chunk-based input unit that balances 3D context preservation with computational efficiency. Our framework partitions the volume into superpatches and employs a 3D masked autoencoder strategy with a dualmasking strategy to learn comprehensive spatial representations. We validated our approach on three diverse large-scale public CT datasets. Our experimental results show that MAESIL demonstrates significant improvements over existing methods such as AE, VAE and VQ-VAE in key reconstruction metrics such as PSNR and SSIM. This establishes MAESIL as a robust and practical pre-training solution for 3D medical imaging tasks.

Other0 citations2026-01-04Paper ->

Intelligent average utility pattern analysis using pre-large concept in dynamic stream data

Doyoung Kim, Seongbin Park, Junyoung Park, Hanju Kim, Seungwan Park et al.

Recent studies on high average utility pattern analysis aim to extract patterns from quantitative data considering the pattern length in incremental environments. However, traditional methods have the limitation that the pattern expansion process is conducted whenever incremental data occur. The pre-large concept is a technique that addresses this by classifying patterns and leveraging them to reduce re-scan and pattern expansion operations with a re-scan condition. In this paper, a novel approach is proposed for analyzing high average utility patterns leveraging the framework of the pre-large concept with the tight re-scan condition. Specifically, the proposed approach adopts a newly proposed tight re-scan condition combined with effective pattern tree management. This approach manages the occurrence of the pattern expansion process more efficiently than state-of-the-art methods and reduces redundant computations while extracting results through the average utility of each pattern. Comprehensive experiments on real and synthetic datasets demonstrate that the proposed method is superior to other comparison methods regarding runtime and scalability while exhibiting completeness with competitive memory usage. Furthermore, the sensitivity tests indicate that the proposed approach maintains the most stable runtime performance under varying thresholds, and the case study under concept drift tests demonstrates its superior scalability, showing its applicability compared to the state-of-the-art approach.

MPC/Planning0 citations2026-01-01Paper ->

Characterizing Carbon Cost of Federated Learning

Yonglak Son, Chanwoo Cho, Seongbin Park, Young Seo Lee, Young Geun Kim

Federated learning (FL) is a decentralized learning approach for training machine learning models without sharing user data with a centralized server. Though FL is considered as a practical solution to mitigate the risk of privacy leakage in training, its environmental impact can be significant, especially considering the scale of billions of mobile users. In this letter, we first demonstrate the carbon cost of privacy by quantifying and characterizing the carbon footprint (CF) of FL while accounting for both server-side FL settings and client heterogeneity. Our analysis reveals that CF-optimal FL settings vary by the service-level objective, and client heterogeneity further complicates CF optimization of FL. We believe our work will be a practical guideline for designing carbon-efficient FL systems.

Learning0 citations2026Paper ->

Mining temporally aware patterns with fuzzy utility measures under dynamically moving window environments

Doyoung Kim, Seongbin Park, Junyoung Park, Hyeonmo Kim, Taewoong Ryu et al.

Other4 citations2025-07-01Paper ->

Pre-Eminent Utility Driven Data Analytics Based on Prelarge Patterns for Dynamic Transaction Deletion in IoT Environments

Doyoung Kim, Seungwan Park, Heonho Kim, Chanhee Lee, Hanju Kim et al.

On the Internet of Things (IoT) environment, interconnected devices continuously share generated data in real time, typically collected with a specific purpose. To ensure efficiency, IoT technology must deliver only the most relevant insights into these devices. High utility pattern mining is a technique that extracts important knowledge, and there has been research on performance improvements to efficiently mine these patterns in dynamic environments. Although approaches with a prelarge concept have been introduced to mining high utility patterns in data deletion environments, the state-of-the-art method relies on inefficient data structures, making them unsuitable for real-time analysis with IoT data. To overcome these limitations, this article proposes a novel utility pattern mining approach with prelarge concept for dynamic IoT environments, where data is deleted because of sensor errors or storage constraints. The actual utilities of the prelarge patterns are maintained to skip the verification and improve communication delays. It can optimize processing time and memory consumption due to storing fewer large or prelarge patterns based on the actual utility. The proposed method operates in an efficient list-based manner, enabling effective search space pruning when the rescan condition is met and generating compact data structures through transaction merging. The experiments indicate that our algorithm is outstanding regarding processing time and scalability with minimal compromise in memory consumption compared with the existing methods, while extracting the exact patterns. Additionally, an analysis that replicates real IoT environments demonstrates that the proposed method is sufficiently applicable in real-world settings.

Other5 citations2025-06-01Paper ->

Efficient mining of incremental high utility patterns with negative unit profits over all the accumulated stream data

Doyoung Kim, Heonho Kim, Seungwan Park, Hanju Kim, Myungha Cho et al.

Robotics0 citations2025-05-22arXiv ->

SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models

Hossein Khalili, Seongbin Park, Venkat Bollapragada, Nader Sehatbakhsh

As vision-based machine learning models are increasingly integrated into autonomous and cyber-physical systems, concerns about (physical) adversarial patch attacks are growing. While state-of-the-art defenses can achieve certified robustness with minimal impact on utility against highly-concentrated localized patch attacks, they fall short in two important areas: (i) State-of-the-art methods are vulnerable to low-noise distributed patches where perturbations are subtly dispersed to evade detection or masking, as shown recently by the DorPatch attack; (ii) Achieving high robustness with state-of-the-art methods is extremely time and resource-consuming, rendering them impractical for latency-sensitive applications in many cyber-physical systems. To address both robustness and latency issues, this paper proposes a new defense strategy for adversarial patch attacks called SuperPure. The key novelty is developing a pixel-wise masking scheme that is robust against both distributed and localized patches. The masking involves leveraging a GAN-based super-resolution scheme to gradually purify the image from adversarial patches. Our extensive evaluations using ImageNet and two standard classifiers, ResNet and EfficientNet, show that SuperPure advances the state-of-the-art in three major directions: (i) it improves the robustness against conventional localized patches by more than 20%, on average, while also improving top-1 clean accuracy by almost 10%; (ii) It achieves 58% robustness against distributed patch attacks (as opposed to 0% in state-of-the-art method, PatchCleanser); (iii) It decreases the defense end-to-end latency by over 98% compared to PatchCleanser. Our further analysis shows that SuperPure is robust against white-box attacks and different patch sizes. Our code is open-source.

Other7 citations2025-02-19Paper ->

Design of a Serendipity-Incorporated Recommender System

Yuri Kim, Seoyeon Oh, Chaerin Noh, Eunbeen Hong, Seongbin Park

Unexpected yet advantageous findings, often referred to as serendipitous discoveries, are becoming increasingly significant in the field of computer science. This research aims to examine the impact of factors that could potentially trigger such serendipity within a recommender system (RS) and consequently proposes a novel, serendipity-incorporated recommender system (SRS). The SRS is developed by integrating elements that could stimulate the occurrence of serendipity into an RS algorithm. These elements include interestingness, diversity, and unexpectedness. As a result, the SRS is equipped to provide users with recommendations that are surprising, intriguing, and atypical. The algorithm within the SRS recommends three items predicated on a user’s preferred item. To facilitate the selection of items to be recommended, we have designed a computation method called the ’serendipity measure’, which is tasked with calculating the weights of all items. Our innovative algorithm and its efficient execution are expounded upon extensively in this study. The performance of the SRS was assessed using a quantitative serendipity evaluation model (QSEM). This model is a quantitative tool designed to measure the probability of users encountering serendipitous events within a specific information space. We conducted a user study to compare the SRS with the traditional cold-start recommender system (CRS), and the feedback for the SRS was positively received. The experiments confirm the viability of cultivating a serendipitous environment from a system’s perspective. The test results also underline the exciting potential that serendipity brings to recommender systems.

Other9 citations2025-02-17Paper ->

A Rule-Based Stock Trading Recommendation System Using Sentiment Analysis and Technical Indicators

Yuri Kim, Sujin Yoo, Seongbin Park

This paper presents a stock trading recommendation system that integrates news sentiment analysis with the relative strength index (RSI) to provide informed buy–sell decisions. The system uses a rule-based natural language processing (NLP) approach to analyze recent news articles and combines the resulting sentiment scores with the RSI, which tracks stock momentum. By evaluating seven days of news data, the system assigns a sentiment score (1 to 100) that reflects market sentiment, while the RSI identifies overbought or oversold conditions. This combined approach allows traders to make data-driven buy, sell, or hold decisions in real time. In this study, we conducted a comparative study with benchmark indices across various subsets of stocks to evaluate their relative performance, highlighting our system’s competitive edge in terms of accuracy, profitability, and lightweight design with low computational cost. The results showed the system’s adaptability across different market segments and its potential to enhance trading outcomes. By integrating real-time sentiment analysis with technical indicators, the system offers a practical and actionable investment strategy.

Other4 citations2025-02-01Paper ->

Dietary Arginine Supplementation Modulates the Proteome of Boar Seminal Plasma

E. Oladejo, Tasha R Gruhot, Seongbin Park, G. Ishak, B. Mote et al.

Simple Summary This study explores the effects of an increased arginine level in a boar diet on semen production and the seminal plasma proteome. The results showed that although arginine supplementation did not significantly affect semen output or sperm quality, such as in motility and morphology, it led to an increase in ten proteins and a decrease in two proteins related to reproduction. These findings suggest that arginine may influence sperm function, highlighting the need for further research in this critical area.

Other3 citations2025Paper ->

Chimera: Creating Digitally Signed Fake Photos by Fooling Image Recapture and Deepfake Detectors

Seongbin Park, Alexander Vilesov, Jinghui Zhang, Hossein Khalili, Yuan Tian et al.

CBF Related Papers
Robotics0 citations2026-06-08arXiv ->

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models

Seongbin Park, Fan Zhang, Baharan Mirzasoleiman, Shahriar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees against collisions with task-irrelevant objects in the scene. Existing safety filters sidestep this problem by querying a vision-language model (VLM) to identify obstacles and their locations. This, however, is too slow to run in the control loop and can only be invoked at episode initialization, leaving the filter unable to track moving obstacles. We discover that a small number of attention heads within a VLA model reliably localize the object the policy intends to approach. These heads can be exploited within a training-free safety framework that obtains the active target from the attention heads at every step, treats the remainder of the scene as obstacles, and feeds these into a Control Barrier Function (CBF) filter. Together with a lightweight real-time object tracker, this allows for collision avoidance for non-static obstacles. We evaluate our framework on SafeLIBERO, which we extend with moving obstacles. On the original static benchmark, our method performs comparably to an oracle that uses privileged simulator state to identify the target, emulating a VLM-based identification step run once at episode initialization. On the dynamic variant, where the oracle's init-time target assignment becomes stale, our method substantially outperforms it by 43%, on average. Our findings suggest that the perceptual signals needed for real-time safety filtering are already present within VLA policies and can be exploited without additional training or heavy auxiliary models.

Robotics0 citations2026-06-08arXiv ->

ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

Fan Zhang, Seongbin Park, Baharan Mirzasoleiman, Shariar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution, yet their generalization capabilities remain fundamentally limited. They3 lack the robustness required to handle perturbations, frequently failing when con-4 fronted with lighting changes, altered camera viewpoints, or small initial-state5 variations. We propose PROBEACT, a training-free runtime intervention frame-6 work that detects and recovers from grasping and placement failures in pre-7 trained VLA policies without modifying their weights or requiring additional8 demonstrations. PROBEACT combines three components: (i) a lightweight multi-9 target hidden-state probe that predicts the 3D positions of task-relevant objects10 from intermediate VLA features, with Hungarian-matched identity tracking for11 multi-object scenes; (ii) an object-agnostic kinematic state machine that detects12 grasp, transport, and placement failures using only gripper-internal signals and13 end-effector kinematics; and (iii) a hierarchical Control Barrier Function (CBF)14 filter that encodes repeated-failure locations as soft safe-set constraints, mini-15 mally correcting VLA actions while preserving baseline behavior. As a plug-and-16 play, training-free intervention loop, PROBEACT is orthogonal to existing train-17 ing pipelines. Evaluated on the LIBERO-plus benchmark, our framework acts as18 a universal safety net, improving the success rate of the OpenVLA-OFT model19 from 69.6% to 74.1%, while demonstrating broad applicability to both base and20 fine-tuned VLA policies.

Robotics0 citations2026-06-08arXiv ->

ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

Fan Zhang, Seongbin Park, Baharan Mirzasoleiman, S. Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution, yet their generalization capabilities remain fundamentally limited. They3 lack the robustness required to handle perturbations, frequently failing when con-4 fronted with lighting changes, altered camera viewpoints, or small initial-state5 variations. We propose PROBEACT, a training-free runtime intervention frame-6 work that detects and recovers from grasping and placement failures in pre-7 trained VLA policies without modifying their weights or requiring additional8 demonstrations. PROBEACT combines three components: (i) a lightweight multi-9 target hidden-state probe that predicts the 3D positions of task-relevant objects10 from intermediate VLA features, with Hungarian-matched identity tracking for11 multi-object scenes; (ii) an object-agnostic kinematic state machine that detects12 grasp, transport, and placement failures using only gripper-internal signals and13 end-effector kinematics; and (iii) a hierarchical Control Barrier Function (CBF)14 filter that encodes repeated-failure locations as soft safe-set constraints, mini-15 mally correcting VLA actions while preserving baseline behavior. As a plug-and-16 play, training-free intervention loop, PROBEACT is orthogonal to existing train-17 ing pipelines. Evaluated on the LIBERO-plus benchmark, our framework acts as18 a universal safety net, improving the success rate of the OpenVLA-OFT model19 from 69.6% to 74.1%, while demonstrating broad applicability to both base and20 fine-tuned VLA policies.

Robotics0 citations2026-06-08arXiv ->

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models

Seongbin Park, Fan Zhang, Baharan Mirzasoleiman, Shahriar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees against collisions with task-irrelevant objects in the scene. Existing safety filters sidestep this problem by querying a vision-language model (VLM) to identify obstacles and their locations. This, however, is too slow to run in the control loop and can only be invoked at episode initialization, leaving the filter unable to track moving obstacles. We discover that a small number of attention heads within a VLA model reliably localize the object the policy intends to approach. These heads can be exploited within a training-free safety framework that obtains the active target from the attention heads at every step, treats the remainder of the scene as obstacles, and feeds these into a Control Barrier Function (CBF) filter. Together with a lightweight real-time object tracker, this allows for collision avoidance for non-static obstacles. We evaluate our framework on SafeLIBERO, which we extend with moving obstacles. On the original static benchmark, our method performs comparably to an oracle that uses privileged simulator state to identify the target, emulating a VLM-based identification step run once at episode initialization. On the dynamic variant, where the oracle's init-time target assignment becomes stale, our method substantially outperforms it by 43%, on average. Our findings suggest that the perceptual signals needed for real-time safety filtering are already present within VLA policies and can be exploited without additional training or heavy auxiliary models.

Non-CBF Papers
Learning0 citationsPaper ->

Which Features are Learned by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression

Yihao Xue, Siddharth Joshi, Eric Gan, Pin-Yu Chen, Baharan Mirzasoleiman

Other0 citationsPaper ->

Data-E � cient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity

Siddharth Joshi, Arnav Jain, Ali Payani, Baharan Mirzasoleiman

Other0 citationsPaper ->

M INI - BATCH C ORESETS FOR M EMORY - EFFICIENT T RAINING OF L ARGE L ANGUAGE M ODELS

Dang Nguyen, Wenhan Yang, Rathul Anand, Yu Yang, Baharan Mirzasoleiman

Learning0 citationsPaper ->

Learning as Reasoning Unfolds: Progressive Rollout Allocation for Efficient Reinforcement Learning

Heyang Jiang, Henry Liu, Baharan Mirzasoleiman

Other0 citationsPaper ->

ICML 2026 Workshop on Foundations of Deep Generative Models: Understanding Memorization, Generalization, and Reasoning Why is A+B Better Than B? A Simple Graph Perspective on Task Transfer

Dang Nguyen, Jianhao Huang, Ali Payani, Baharan Mirzasoleiman

Other0 citationsPaper ->

Identifying Spurious Correlations Early in Training through the Lens of Simplicity Bias

Yu Yang, Eric Gan, Gintare Karolina, Dziugaite, Google DeepMind et al.

MPC/Planning0 citations2026-06-25arXiv ->

Reasoning Quality Emerges Early: Data Curation for Reasoning Models

Hongyi Jin, Wenhan Yang, Meysam Ghaffari, Carlos Morato, Baharan Mirzasoleiman

Supervised fine-tuning (SFT) on a small, high-quality set of long reasoning traces is an effective approach for eliciting strong reasoning capabilities in Large Language Models (LLMs). However, existing methods for curating high-quality SFT data rely heavily on strong reasoning models to filter examples based on diversity and difficulty, making the curation process costly while often yielding suboptimal data quality. In this work, we show that diverse and challenging reasoning examples can be identified using only the initial reasoning tokens. Specifically, we demonstrate that difficult problems can be reliably detected based on the loss of the first 100 reasoning tokens evaluated at a randomly perturbed checkpoint of the pretrained model. We further show that examples exhibiting similar loss patterns over their first 1k reasoning tokens across a small number of perturbed checkpoints extrapolating along the fine-tuning trajectory provably induce similar gradients. We validate our approach through extensive experiments on fine-tuning Qwen2.5-7B and Llama3.1-8B models on the M23K medical reasoning and OpenThoughts-Math datasets. Our method outperforms existing baselines by up to 1.7% while being 91% more token efficient.

MPC/Planning0 citations2026-04-13arXiv ->

How Transformers Learn to Plan via Multi-Token Prediction

Jianhao Huang, Zhanpeng Zhou, Renqiu Xia, Baharan Mirzasoleiman, Weijie J. Su et al.

While next-token prediction (NTP) has been the standard objective for training language models, it often struggles to capture global structure in reasoning tasks. Multi-token prediction (MTP) has recently emerged as a promising alternative, yet its underlying mechanisms remain poorly understood. In this paper, we study how MTP facilitates reasoning, with a focus on planning. Empirically, we show that MTP consistently outperforms NTP on both synthetic graph path-finding tasks and more realistic reasoning benchmarks, such as Countdown and boolean satisfiability problems. Theoretically, we analyze a simplified two-layer Transformer on a star graph task. We prove that MTP induces a two-stage reverse reasoning process: the model first attends to the end node and then reconstructs the path by tracing intermediate nodes backward. This behavior arises from a gradient decoupling property of MTP, which provides a cleaner training signal compared to NTP. Ultimately, our results highlight how multi-token objectives inherently bias optimization toward robust and interpretable reasoning circuits.

Learning0 citations2026-03-01arXiv ->

Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models

Adel Javanmard, Baharan Mirzasoleiman, V. Mirrokni

Large Language Models (LLMs) are pretrained on massive datasets and later instruction-tuned via supervised fine-tuning (SFT) or reinforcement learning (RL). Best practices emphasize large, diverse pretraining data, whereas post-training operates differently: SFT relies on smaller, high-quality datasets, while RL benefits more from scale, with larger amounts of feedback often outweighing label quality. Yet it remains unclear why pretraining and RL require large datasets, why SFT excels on smaller ones, and what defines high-quality SFT data. In this work, we theoretically analyze transformers trained on an in-context weight prediction task for linear regression. Our analysis reveals several key findings: $(i)$ balanced pretraining data can induce latent capabilities later activated during post-training, and $(ii)$ SFT learns best from a small set of examples challenging for the pretrained model, while excessively large SFT datasets may dilute informative pretraining signals. In contrast, RL is most effective on large-scale data that is not overly difficult for the pretrained model. We validate these theoretical insights with experiments on large nonlinear transformer architectures.

Other0 citations2026-01-31arXiv ->

Data Distribution as a Lever for Guiding Optimizers Toward Superior Generalization in LLMs

Tushaar Gangavarapu, Jiping Li, Christopher Vattheuer, Zhangyang Wang, Baharan Mirzasoleiman

Can modifying the training data distribution guide optimizers toward solutions with improved generalization when training large language models (LLMs)? In this work, we theoretically analyze an in-context linear regression model with multi-head linear self-attention, and compare the training dynamics of two gradient based optimizers, namely gradient descent (GD) and sharpness-aware minimization (SAM), the latter exhibiting superior generalization properties but is prohibitively expensive for training even medium-sized LLMs. We show, for the first time, that SAM induces a lower simplicity bias (SB)-the tendency of an optimizer to preferentially learn simpler features earlier in training-and identify this reduction as a key factor underlying its improved generalization performance. Motivated by this insight, we demonstrate that altering the training data distribution by upsampling or augmenting examples learned later in training similarly reduces SB and leads to improved generalization. Our extensive experiments show that our strategy improves the performance of multiple LLMs-including Phi2-2.7B , Llama3.2-1B, Gemma3-1B-PT, and Qwen3-0.6B-Base-achieving relative accuracy gains up to 18% when fine-tuned with AdamW and Muon on mathematical reasoning tasks.

Theory0 citations2026-01-31arXiv ->

Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision

Yihao Xue, Allan N. Zhang, Jianhao Huang, A. Sahai, Baharan Mirzasoleiman

Training LLMs to think and reason for longer has become a key ingredient in building state-of-the-art models that can solve complex problems previously out of reach. Recent efforts pursue this in different ways, such as RL fine-tuning to elicit long CoT or scaling latent reasoning through architectural recurrence. This makes reasoning length an important scaling knob. In this work, we identify a novel phenomenon (both theoretically and experimentally): under outcome-only supervision, out-of-distribution (OOD) performance can continue improving as training-time reasoning length (e.g., the token budget in RL, or the loop count in looped Transformers) increases, even after in-distribution (ID) performance has saturated. This suggests that robustness may require a larger budget than ID validation alone would indicate. We provide theoretical explanations via two mechanisms: (i) self-iteration can induce a stronger inductive bias in the hypothesis class, reshaping ID-optimal solutions in ways that improve OOD generalization; and (ii) when shortcut solutions that work for ID samples but not for OOD samples persist in the hypothesis class, regularization can reduce the learned solution's reliance on these shortcuts as the number of self-iterations increases. We complement the theory with empirical evidence from two realizations of scaling training-time reasoning length: increasing the number of loops in looped Transformers on a synthetic task, and increasing token budgets during RL fine-tuning of LLMs on mathematical reasoning.

Learning0 citations2026-01-30arXiv ->

Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from k-Parity

Jianhao Huang, Baharan Mirzasoleiman

Masked Diffusion Language Models have recently emerged as a powerful generative paradigm, yet their generalization properties remain understudied compared to their auto-regressive counterparts. In this work, we investigate these properties within the setting of the $k$-parity problem (computing the XOR sum of $k$ relevant bits), where neural networks typically exhibit grokking -- a prolonged plateau of chance-level performance followed by sudden generalization. We theoretically decompose the Masked Diffusion (MD) objective into a Signal regime which drives feature learning, and a Noise regime which serves as an implicit regularizer. By training nanoGPT using MD objective on the $k$-parity problem, we demonstrate that MD objective fundamentally alters the learning landscape, enabling rapid and simultaneous generalization without experiencing grokking. Furthermore, we leverage our theoretical insights to optimize the distribution of the mask probability in the MD objective. Our method significantly improves perplexity for 50M-parameter models and achieves superior results across both pre-training from scratch and supervised fine-tuning. Specifically, we observe performance gains peaking at $8.8\%$ and $5.8\%$, respectively, on 8B-parameter models, confirming the scalability and effectiveness of our framework in large-scale masked diffusion language model regimes.

Other5 citations2025-10-04arXiv ->

Understanding the Role of Training Data in Test-Time Scaling

Adel Javanmard, Baharan Mirzasoleiman, V. Mirrokni

Test-time scaling improves the reasoning capabilities of large language models (LLMs) by allocating extra compute to generate longer Chains-of-Thoughts (CoTs). This enables models to tackle more complex problem by breaking them down into additional steps, backtracking, and correcting mistakes. Despite its strong performance--demonstrated by OpenAI's o1 and DeepSeek R1, the conditions in the training data under which long CoTs emerge, and when such long CoTs improve the performance, remain unclear. In this paper, we study the performance of test-time scaling for transformers trained on an in-context weight prediction task for linear regression. Our analysis provides a theoretical explanation for several intriguing observations: First, at any fixed test error, increasing test-time compute allows us to reduce the number of in-context examples (context length) in training prompts. Second, if the skills required to solve a downstream task are not sufficiently present in the training data, increasing test-time compute can harm performance. Finally, we characterize task hardness via the smallest eigenvalue of its feature covariance matrix and show that training on a diverse, relevant, and hard set of tasks results in best performance for test-time scaling. We confirm our findings with experiments on large, nonlinear transformer architectures.

Learning0 citations2025-10-01arXiv ->

Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories

Nilay Naharas, Dang Nguyen, Nesihan Bulut, M. Bateni, V. Mirrokni et al.

Data-efficient learning aims to eliminate redundancy in large training datasets by training models on smaller subsets of the most informative examples. While data selection has been extensively explored for vision models and large language models (LLMs), it remains underexplored for Large Vision-Language Models (LVLMs). Notably, none of existing methods can outperform random selection at different subset sizes. In this work, we propose the first principled method for data-efficient instruction tuning of LVLMs. We prove that examples with similar cross-modal attention matrices during instruction tuning have similar gradients. Thus, they influence model parameters in a similar manner and convey the same information to the model during training. Building on this insight, we propose XMAS, which clusters examples based on the trajectories of the top singular values of their attention matrices obtained from fine-tuning a small proxy LVLM. By sampling a balanced subset from these clusters, XMAS effectively removes redundancy in large-scale LVLM training data. Extensive experiments show that XMAS can discard 50% of the LLaVA-665k dataset and 85% of the Vision-Flan dataset while fully preserving performance of LLaVA-1.5-7B on 10 downstream benchmarks and speeding up its training by 1.2x. This is 30% more data reduction compared to the best baseline for LLaVA-665k. The project's website can be found at https://bigml-cs-ucla.github.io/XMAS-project-page/.

Other0 citations2025-07-22arXiv ->

LoRA is All You Need for Safety Alignment of Reasoning LLMs

Yihao Xue, Baharan Mirzasoleiman

Reasoning-capable LLMs have achieved major breakthroughs in solving complex problems, but recent work shows that acquiring and deploying strong reasoning can introduce significant safety risks. A common mitigation is to apply a secondary safety-alignment phase after reasoning is learned; however, safety alignment often degrades reasoning performance--a phenomenon known as the"Safety Tax". In this work, we show that a simple approach can largely bypass this trade-off: applying LoRA during SFT on refusal datasets. Despite its simplicity, this recipe achieves safety comparable to full-model alignment while preserving reasoning performance close to the original reasoning-tuned model, and the result holds across multiple model sizes and architectures, two safety benchmarks, and four reasoning benchmarks spanning mathematics, science, and code generation. We further ablate LoRA configurations and find that (1) rank-1 updates are sufficient to achieve the best safety-reasoning trade-off, (2) applying LoRA only to the MLP up-projection layers can outperform updating the full MLP, and (3) updating middle layers is more effective than updating early or late layers. Finally, we provide a theoretical analysis that helps understand when and why LoRA works, revealing that overshooting the rank budget (using a larger rank than needed for the finetuning task) induces base-task degradation at a rate inversely proportional to the intrinsic dimensionality of the base task. This suggests LoRA is most effective when the finetuning task is low-rank and the base capability is high-rank.

Other0 citations2025-05-30arXiv ->

Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity

Dang Nguyen, Ali Payani, Baharan Mirzasoleiman

Hallucination in large language models (LLMs) can be detected by assessing the uncertainty of model outputs, typically measured using entropy. Semantic entropy (SE) enhances traditional entropy estimation by quantifying uncertainty at the semantic cluster level. However, as modern LLMs generate longer one-sentence responses, SE becomes less effective because it overlooks two crucial factors: intra-cluster similarity (the spread within a cluster) and inter-cluster similarity (the distance between clusters). To address these limitations, we propose a simple black-box uncertainty quantification method inspired by nearest neighbor estimates of entropy. Our approach can also be easily extended to white-box settings by incorporating token probabilities. Additionally, we provide theoretical results showing that our method generalizes semantic entropy. Extensive empirical results demonstrate its effectiveness compared to semantic entropy across two recent LLMs (Phi3 and Llama3) and three common text generation tasks: question answering, text summarization, and machine translation. Our code is available at https://github.com/BigML-CS-UCLA/SNNE.

Theory0 citations2025-05-30arXiv ->

Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap

Wenhan Yang, Spencer M. Stice, Ali Payani, Baharan Mirzasoleiman

Ensuring Vision-Language Models (VLMs) generate safe outputs is crucial for their reliable deployment. However, LVLMs suffer from drastic safety degradation compared to their LLM backbone. Even blank or irrelevant images can trigger LVLMs to generate harmful responses to prompts that would otherwise be refused in text-only contexts. The modality gap between image and text representations has been recently hypothesized to contribute to safety degradation of LVLMs. However, if and how the amount of modality gap affects LVLMs' safety is not studied. In this work, we show that the amount of modality gap is highly inversely correlated with VLMs' safety. Then, we show that this modality gap is introduced during pretraining LVLMs and persists through fine-tuning. Inspired by this observation, we propose a regularization to reduce the modality gap during pretraining. Our extensive experiments on LLaVA v1.5, ShareGPT4V, and MiniGPT-4 show that our method substantially improves safety alignment of LVLMs, reducing unsafe rate by up to 16.3% without compromising performance, and can further boost existing defenses by up to 18.2%.

Learning2 citations2025-05-27arXiv ->

Do We Need All the Synthetic Data? Targeted Image Augmentation via Diffusion Models

Dang Nguyen, Jiping Li, Jinghao Zheng, Baharan Mirzasoleiman

Synthetically augmenting training datasets with diffusion models has become an effective strategy for improving the generalization of image classifiers. However, existing approaches typically increase dataset size by 10-30x and struggle to ensure generation diversity, leading to substantial computational overhead. In this work, we introduce TADA (TArgeted Diffusion Augmentation), a principled framework that selectively augments examples that are not learned early in training using faithful synthetic images that preserve semantic features while varying noise. We show that augmenting only this targeted subset consistently outperforms augmenting the entire dataset. Through theoretical analysis on a two-layer CNN, we prove that TADA improves generalization by promoting homogeneity in feature learning speed without amplifying noise. Extensive experiments demonstrate that by augmenting only 30-40% of the training data, TADA improves generalization by up to 2.8% across diverse architectures including ResNet, ViT, ConvNeXt, and Swin Transformer on CIFAR-10/100, TinyImageNet, and ImageNet, using optimizers such as SGD and SAM. Notably, TADA combined with SGD outperforms the state-of-the-art optimizer SAM on CIFAR-100 and TinyImageNet. Furthermore, TADA shows promising improvements on object detection benchmarks, demonstrating its applicability beyond image classification. Our code is available at https://github.com/BigML-CS-UCLA/TADA.

MPC/Planning14 citations2025-05-19arXiv ->

DD-Ranking: Rethinking the Evaluation of Dataset Distillation

Zekai Li, Xinhao Zhong, Samir Khaki, Zhiyuan Liang, Yuhao Zhou et al.

In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance comparable to those trained on the original datasets. To further improve the performance of synthetic datasets, various training pipelines and optimization objectives have been proposed, greatly advancing the field of dataset distillation. Recent decoupled dataset distillation methods introduce soft labels and stronger data augmentation during the post-evaluation phase and scale dataset distillation up to larger datasets (e.g., ImageNet-1K). However, this raises a question: Is accuracy still a reliable metric to fairly evaluate dataset distillation methods? Our empirical findings suggest that the performance improvements of these methods often stem from additional techniques rather than the inherent quality of the images themselves, with even randomly sampled images achieving superior results. Such misaligned evaluation settings severely hinder the development of DD. Therefore, we propose DD-Ranking, a unified evaluation framework, along with new general evaluation metrics to uncover the true performance improvements achieved by different methods. By refocusing on the actual information enhancement of distilled datasets, DD-Ranking provides a more comprehensive and fair evaluation standard for future research advancements.

Other0 citations2025-02-24arXiv ->

Synthetic Text Generation for Training Large Language Models via Gradient Matching

Dang Nguyen, Zeman Li, M. Bateni, V. Mirrokni, Meisam Razaviyayn et al.

Synthetic data has the potential to improve the performance, training efficiency, and privacy of real training examples. Nevertheless, existing approaches for synthetic text generation are mostly heuristics and cannot generate human-readable text without compromising the privacy of real data, or provide performance guarantees for training Large Language Models (LLMs). In this work, we propose the first theoretically rigorous approach for generating synthetic human-readable text that provides convergence, performance, and privacy guarantees for fine-tuning LLMs on a target task. To do so, we leverage Alternating Direction Method of Multipliers (ADMM) that iteratively optimizes the embeddings of synthetic examples to match the noisy gradient of the target training or validation data, and maps them to a sequence of text tokens with low perplexity. In doing so, the generated synthetic text guarantees convergence of the model to a close neighborhood of the solution obtained by fine-tuning on real data and preserves their privacy. Experiments on various classification tasks confirm the effectiveness of our proposed approach. Our code is available at https://github.com/BigML-CS-UCLA/GRADMM.

CBF Related Papers
Robotics0 citations2026-06-08arXiv ->

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models

Seongbin Park, Fan Zhang, Baharan Mirzasoleiman, Shahriar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees against collisions with task-irrelevant objects in the scene. Existing safety filters sidestep this problem by querying a vision-language model (VLM) to identify obstacles and their locations. This, however, is too slow to run in the control loop and can only be invoked at episode initialization, leaving the filter unable to track moving obstacles. We discover that a small number of attention heads within a VLA model reliably localize the object the policy intends to approach. These heads can be exploited within a training-free safety framework that obtains the active target from the attention heads at every step, treats the remainder of the scene as obstacles, and feeds these into a Control Barrier Function (CBF) filter. Together with a lightweight real-time object tracker, this allows for collision avoidance for non-static obstacles. We evaluate our framework on SafeLIBERO, which we extend with moving obstacles. On the original static benchmark, our method performs comparably to an oracle that uses privileged simulator state to identify the target, emulating a VLM-based identification step run once at episode initialization. On the dynamic variant, where the oracle's init-time target assignment becomes stale, our method substantially outperforms it by 43%, on average. Our findings suggest that the perceptual signals needed for real-time safety filtering are already present within VLA policies and can be exploited without additional training or heavy auxiliary models.

Robotics0 citations2026-06-08arXiv ->

ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

Fan Zhang, Seongbin Park, Baharan Mirzasoleiman, Shariar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution, yet their generalization capabilities remain fundamentally limited. They3 lack the robustness required to handle perturbations, frequently failing when con-4 fronted with lighting changes, altered camera viewpoints, or small initial-state5 variations. We propose PROBEACT, a training-free runtime intervention frame-6 work that detects and recovers from grasping and placement failures in pre-7 trained VLA policies without modifying their weights or requiring additional8 demonstrations. PROBEACT combines three components: (i) a lightweight multi-9 target hidden-state probe that predicts the 3D positions of task-relevant objects10 from intermediate VLA features, with Hungarian-matched identity tracking for11 multi-object scenes; (ii) an object-agnostic kinematic state machine that detects12 grasp, transport, and placement failures using only gripper-internal signals and13 end-effector kinematics; and (iii) a hierarchical Control Barrier Function (CBF)14 filter that encodes repeated-failure locations as soft safe-set constraints, mini-15 mally correcting VLA actions while preserving baseline behavior. As a plug-and-16 play, training-free intervention loop, PROBEACT is orthogonal to existing train-17 ing pipelines. Evaluated on the LIBERO-plus benchmark, our framework acts as18 a universal safety net, improving the success rate of the OpenVLA-OFT model19 from 69.6% to 74.1%, while demonstrating broad applicability to both base and20 fine-tuned VLA policies.

Robotics0 citations2026-06-08arXiv ->

ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

Fan Zhang, Seongbin Park, Baharan Mirzasoleiman, S. Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution, yet their generalization capabilities remain fundamentally limited. They3 lack the robustness required to handle perturbations, frequently failing when con-4 fronted with lighting changes, altered camera viewpoints, or small initial-state5 variations. We propose PROBEACT, a training-free runtime intervention frame-6 work that detects and recovers from grasping and placement failures in pre-7 trained VLA policies without modifying their weights or requiring additional8 demonstrations. PROBEACT combines three components: (i) a lightweight multi-9 target hidden-state probe that predicts the 3D positions of task-relevant objects10 from intermediate VLA features, with Hungarian-matched identity tracking for11 multi-object scenes; (ii) an object-agnostic kinematic state machine that detects12 grasp, transport, and placement failures using only gripper-internal signals and13 end-effector kinematics; and (iii) a hierarchical Control Barrier Function (CBF)14 filter that encodes repeated-failure locations as soft safe-set constraints, mini-15 mally correcting VLA actions while preserving baseline behavior. As a plug-and-16 play, training-free intervention loop, PROBEACT is orthogonal to existing train-17 ing pipelines. Evaluated on the LIBERO-plus benchmark, our framework acts as18 a universal safety net, improving the success rate of the OpenVLA-OFT model19 from 69.6% to 74.1%, while demonstrating broad applicability to both base and20 fine-tuned VLA policies.

Robotics0 citations2026-06-08arXiv ->

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models

Seongbin Park, Fan Zhang, Baharan Mirzasoleiman, Shahriar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees against collisions with task-irrelevant objects in the scene. Existing safety filters sidestep this problem by querying a vision-language model (VLM) to identify obstacles and their locations. This, however, is too slow to run in the control loop and can only be invoked at episode initialization, leaving the filter unable to track moving obstacles. We discover that a small number of attention heads within a VLA model reliably localize the object the policy intends to approach. These heads can be exploited within a training-free safety framework that obtains the active target from the attention heads at every step, treats the remainder of the scene as obstacles, and feeds these into a Control Barrier Function (CBF) filter. Together with a lightweight real-time object tracker, this allows for collision avoidance for non-static obstacles. We evaluate our framework on SafeLIBERO, which we extend with moving obstacles. On the original static benchmark, our method performs comparably to an oracle that uses privileged simulator state to identify the target, emulating a VLM-based identification step run once at episode initialization. On the dynamic variant, where the oracle's init-time target assignment becomes stale, our method substantially outperforms it by 43%, on average. Our findings suggest that the perceptual signals needed for real-time safety filtering are already present within VLA policies and can be exploited without additional training or heavy auxiliary models.

Non-CBF Papers
Learning3 citations2026-08-01Paper ->

BISen: A Robust Framework for Efficient CNN Inference on Battery-Free Intelligent Sensory Nodes

Sepehr Tabrizchi, Shayan Gerami, Justin Feng, Nader Sehatbakhsh, David Z. Pan et al.

We present BISen, a framework for efficient and reliable convolutional neural network (CNN) inference on battery-free, energy-harvesting IoT sensor nodes. Battery-powered deployments suffer from limited lifetimes, high replacement costs, and environmental impacts, problems that will intensify as IoT scales to billions of devices. Energy-harvesting nodes remove batteries but face intermittent power, resulting in frequent failures that corrupt the intermediate CNN state, require costly checkpointing and rollback, and amplify non-volatile memory (NVM) traffic under tight on-chip memory constraints, leaving little harvested energy for useful sensing and inference. BISen introduces a reactive intermittent execution model for CNN workloads on off-the-shelf ultra-low-power microcontrollers. An energy-aware state machine with a safe-stop mechanism halts execution before brownout, while selective checkpointing preserves only the minimal CNN state needed for forward progress. This enables seamless resumption across power cycles while sharply reducing NVM reads/writes and memory-access overheads. Across two commercial MCU+radio platforms, three real harvested power traces, and nine CNNs, BISen cuts NVM operations by up to 86.4%, reduces standby/load/store operations by up to 94.1%, 94.5%, and 90.7%, and improves sensing throughput by about $1.3{-}1.4\boldsymbol{\times}$1.31.4× compared to a state-of-the-art reactive baseline under the same energy budget, enabling long-lived, battery-free, carbon-aware IoT deployments.

MPC/Planning0 citations2026-06-27arXiv ->

SHIFT: Dynamic Compute Relocation Framework for Communication-Aware Chiplet-Based Systems

Arvin Delavari, Leonid Popryho, Sneha Swaroopa, Nader Sehatbakhsh, Inna Partin-Vaisband et al.

The increasing communication complexity of large-scale heterogeneous systems has motivated runtime methodologies for communication-aware workload placement and routing optimization. These communication limitations are addressed in this paper by proposing SHIFT, a novel topology-agnostic approach that transfers compute node context and data to a more suitably positioned node, rather than only shifting data as in conventional networks-on-chip. The proposed strategy is evaluated on a chiplet-based architecture utilizing a fine-pitch integration platform featuring multiple bandwidth-domains for heterogeneous workloads. The proposed architecture employs multi-layered routing between functional or memory chiplets and utility chiplets, which serve as intelligent nodes for routing and compute relocation. Adaptive scheduling and routing utilize a modified shortest-path algorithm for large-scale systems, complemented by a lightweight ML-assisted policy that infers traffic conditions to improve adaptivity. To establish a performance baseline, the initial assessment uses random instruction vectors and data patterns to evaluate the fundamental capabilities of SHIFT. Simulation results exhibit successful relocations over total trials ranging from 75.2% to 97.9% across configurations, with average latency improvements of 16.4%-62.5% and a maximum of 76.8%. In addition, throughput is improved by up to 12.5x, power dissipation per unit area is reduced by ~8%, energy-per-bit is reduced by up to 58.3%, and performance is improved by 18%. To evaluate efficiency under high logic and data density, the framework was tested on standard LLM workloads. Results exhibit average improvements of 4.9x, 5.9x, and 1.8x in runtime, throughput, and energy-efficiency, respectively, surpassing state-of-the-art wafer-scale LLM services and demonstrating compatibility with large-scale platforms and applications.

Learning0 citations2026-06-22Paper ->

LeakSEAL: Power Side-Channel Leakage Analysis and Mitigation for Secure Edge AI Learning

Veeramani Pugazhenthi, Muhtasim Alam Chowdhury, S. Ghimire, Harish Kumar Dharavath, Parsa Mirfasihi et al.

On-chip learning enables machine learning models to be trained or updated directly on specialized hardware rather than on external CPUs or GPUs, offering lower latency, improved energy-efficiency, enhanced privacy, and real-time adaptability for edge devices. In Spiking Neural Networks (SNNs), this capability relies on dynamic synaptic weight adaptation, but such adaptability also introduces significant security risks. In this work, we demonstrate a power side-channel attack on a quantized SNN implemented on a CW305 FPGA platform using ChipWhisperer. Our analysis identifies consistent power leakage patterns associated with neuron update operations, allowing an attacker to infer internal model attributes without direct access to the model’s weights or inputs. We further perform Correlation Power Analysis (CPA) with a Hamming Weight leakage model to recover secret synaptic weights with high confidence using as few as 1,500 power traces. These results expose critical vulnerabilities in on-chip learning systems and SNN architectures, highlight realistic threats to IoT and edge applications, and motivate mitigation strategies at the software-hardware boundary, including secure design practices, cryptographic protections, and access control mechanisms, without significantly degrading performance.

Other0 citations2026-06-10arXiv ->

Defense Against Prompt Inversion Attacks: An Information-Theoretic Approach for LLM Collaborative Inference

Sayedeh Leila Noorbakhsh, Hossein Khalili, Nader Sehatbakhsh

Collaborative edge-cloud inference enables resource-constrained devices to leverage large language models (LLMs) by offloading partial computation to cloud servers. However, transmitting intermediate activations exposes sensitive user prompts to prompt inversion attacks, where an adversary reconstructs the original input from shared representations. Existing defenses rely largely on heuristic perturbations or empirical tuning, offering limited theoretical understanding of privacy leakage and its interaction with utility and latency constraints. We propose an information-theoretic defense framework for prompt inversion in collaborative LLM inference. Our approach learns privacy-preserving representations by explicitly minimizing the mutual information between intermediate activations and the input prompt while maintaining task utility under computational constraints. We derive theoretical guarantees on prompt reconstruction error, characterize fundamental privacy-utility tradeoffs, and establish token-level accuracy bounds for downstream inference. We then propose a novel defense based on privacy adapters implemented via low-dimensional information bottlenecks. Extensive experiments across multiple settings demonstrate that our method achieves superior privacy-utility-latency tradeoffs compared to existing defenses (up to 35% reduction in attack success), providing a principled foundation for private and efficient collaborative LLM inference.

Theory0 citations2026-05-10Paper ->

TIRA: Task-Based Intermittent Remote Attestation

Fatemeh Arkannezhad, Nader Sehatbakhsh

Intermittent computing platforms powered by energy harvesting enable sustainable sensing and embedded intelligence in environments without reliable power. Recent advances support robust, task-based execution that tolerates frequent failures and ensures correct event-driven concurrency without the need for costly checkpointing. However, these systems lack basic security features, particularly remote attestation, undermining trust in adversarial or safety-critical settings. We present the first remote attestation framework for task-based intermittent systems, providing static attestation at boot and dynamic attestation across task transitions. By aligning with runtime task boundaries and commit points, our approach enables low-overhead mechanisms that preserve responsiveness and energy efficiency while ensuring proof-of-execution (PoX), remote, and task-flow attestations. These guarantees hold even under power failures and frequent interrupts, making ours the first system to achieve comprehensive attestation in intermittent computing. Our method does not require any hardware modifications; instead, it leverages a compiler–software co-design to securely manage tasks. We implement and formally verify the framework on a TI MSP430-based platform. Evaluation on six benchmarks shows 18% and 4% overhead in runtime and memory, respectively, while achieving remote attestation for task-based intermittent devices. Our framework will be publicly available.

Other0 citations2026-04-08Paper ->

Scalable Security Monitoring on Chiplet-Based Systems

Pooya Aghanoury, Sneha Swaroopa, Dao Xian Ding, F. Firouzi, Nader Sehatbakhsh

To protect emerging AI chiplet-based systems against various attacks, a promising approach is to deploy a distributed network of on-package security modules to monitor individual chiplets. These monitors can be implemented either as active elements integrated within the substrate or as dedicated security helper chiplets. Connected through a secure intrapackage network, these components continuously observe communication among regular chiplets (e.g., CPU, GPU, accelerators) and memory. Additionally, the security chiplets can provide ondemand security services, such as trusted execution environments (TEE) and cryptographic operations, to the functional chiplets. To explore the feasibility, usefulness, and trade-offs of such a design, we study the cost, power, and performance implications of using this model by developing a new framework. Our analysis highlights the cost tradeoffs across different design strategies.

Theory0 citations2026-02-21Paper ->

Attest Like Software: Formally-Verified Software-Programmable Proof of Execution Architecture Using SoC FPGAs

Fatemeh Arkannezhad, Nader Sehatbakhsh

Proof of Execution (PoX) enables a remote verifier to confirm that a specific program executed fully, correctly, and without interference on a potentially compromised device. Existing PoX solutions typically rely on trusted execution environments (TEEs) or custom hardware extensions, which limit their applicability to legacy, cost-sensitive, or resource-constrained embedded platforms. Moreover, many prior designs compromise real-time availability by disabling interrupts, enforcing two-world execution models, or relying on heavyweight isolation mechanisms. These limitations make existing PoX approaches poorly suited for safety-critical cyber-physical systems (CPS), where timing guarantees and responsiveness are as important as security. We present FoX, a software-programmable and formally verified PoX architecture that leverages the embedded FPGA fabric already present in commercial SoC FPGAs as a reconfigurable hardware root of trust (RoT). Unlike prior work, FoX requires no hardware modifications, no trusted operating system, and no specialized co-processors. The FPGA acts as an external observer and enforcer rather than an execution engine, allowing FoX to be retrofitted to deployed and legacy systems while preserving real-time behavior. At the core of FoX is CIMS (Check–Invoke–Monitor–Sign), a four-phase protocol that jointly enforces pre-execution integrity and in-execution correctness. First, FoX performs static attestation by hashing the interrupt vector table and target program memory to ensure code integrity before execution. Second, FoX enforces trusted invocation by embedding the target program within an interrupt service routine (ISR) and explicitly triggering execution via an FPGA-issued interrupt, ensuring the verified code is the one that runs. Third, during execution, FoX performs continuous runtime monitoring using FPGA-based side-channel sensing to detect interrupts, preemption, or concurrent activity. Finally, FoX generates a cryptographically signed proof bound to a fresh verifier challenge, providing strong evidence of faithful execution. A key insight of FoX is its use of ring-oscillator–based power sensors synthesized on the FPGA fabric to monitor execution integrity. Rather than relying on software instrumentation or CPU isolation, FoX detects execution anomalies indirectly by observing characteristic power fluctuations caused by interrupts or control-flow disruptions. This approach is non-invasive, compatible with untrusted software stacks, and resilient to time-of-check-to-time-of-use (TOCTOU) attacks. By continuously monitoring power signals throughout execution, FoX ensures that any interruption or tampering invalidates the proof. FoX is explicitly designed to preserve availability and real-time guarantees. Time-consuming integrity checks execute on the FPGA in parallel with normal CPU operation, and the monitored ISR may be preempted by higher-priority tasks without violating correctness. In such cases, FoX safely restarts the protocol, ensuring atomic execution without blocking interrupts or degrading system responsiveness. We implement FoX on a commercial SoC FPGA (Terasic DE1-SoC) and formally verify its control logic using NuSMV, proving that the design satisfies both static attestation and execution-integrity security games under a strong adversary model that fully compromises system software. Experimental evaluation demonstrates that FoX incurs only 2.5% power overhead and 24% FPGA area overhead, detects execution interruptions with high accuracy (false negatives below 0.3%), and introduces no missed deadlines across representative embedded workloads. Overall, FoX demonstrates that SoC FPGAs can serve as agile, software-defined roots of trust, enabling practical, formally verified PoX for real-time and legacy embedded systems. By combining reconfigurable hardware, side-channel monitoring, and formal verification, FoX bridges the gap between deployability, security, and availability in modern embedded platforms.

Other1 citations2026Paper ->

XR Devices Send WiFi Packets When They Should Not: Cross-Building Keylogging Attacks via Non-Cooperative Wireless Sensing

Christopher Vattheuer, Justin Feng, Hossein Khalili, Nader Sehatbakhsh, Omid Salehi-Abari

Despite

Learning0 citations2025-05-29Paper ->

Developing new solutions for data provenance and deepfake detection using physics, hardware, and machine learning

Nader Sehatbakhsh, Yuan Tian, Achuta Kadambi

As generative machine learning and deepfakes become increasingly important, reliable methods for protecting data provenance and authenticity are essential. Current approaches for verifying data provenance often rely on cryptographic measures. While cryptography can ensure the authenticity of data, it cannot guarantee the honesty/correctness of the data itself; for instance, if a sensor is spoofed, the generated data may be false even before the cryptographic process takes place. This paper introduces this new attack surface, the Physical Layer. We show a real example of how such an attack can be conducted. We then explore various solutions to address this concern, including leveraging hardware, sensing, and physics.

Robotics0 citations2025-05-22arXiv ->

SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models

Hossein Khalili, Seongbin Park, Venkat Bollapragada, Nader Sehatbakhsh

As vision-based machine learning models are increasingly integrated into autonomous and cyber-physical systems, concerns about (physical) adversarial patch attacks are growing. While state-of-the-art defenses can achieve certified robustness with minimal impact on utility against highly-concentrated localized patch attacks, they fall short in two important areas: (i) State-of-the-art methods are vulnerable to low-noise distributed patches where perturbations are subtly dispersed to evade detection or masking, as shown recently by the DorPatch attack; (ii) Achieving high robustness with state-of-the-art methods is extremely time and resource-consuming, rendering them impractical for latency-sensitive applications in many cyber-physical systems. To address both robustness and latency issues, this paper proposes a new defense strategy for adversarial patch attacks called SuperPure. The key novelty is developing a pixel-wise masking scheme that is robust against both distributed and localized patches. The masking involves leveraging a GAN-based super-resolution scheme to gradually purify the image from adversarial patches. Our extensive evaluations using ImageNet and two standard classifiers, ResNet and EfficientNet, show that SuperPure advances the state-of-the-art in three major directions: (i) it improves the robustness against conventional localized patches by more than 20%, on average, while also improving top-1 clean accuracy by almost 10%; (ii) It achieves 58% robustness against distributed patch attacks (as opposed to 0% in state-of-the-art method, PatchCleanser); (iii) It decreases the defense end-to-end latency by over 98% compared to PatchCleanser. Our further analysis shows that SuperPure is robust against white-box attacks and different patch sizes. Our code is open-source.

Learning0 citations2025-04-11arXiv ->

To See or Not to See - Fingerprinting Devices in Adversarial Environments Amid Advanced Machine Learning

Justin Feng, Nader Sehatbakhsh

The increasing use of the Internet of Things raises security concerns. To address this, device fingerprinting is often employed to authenticate devices, detect adversaries, and identify eavesdroppers in an environment. This requires the ability to discern between legitimate and malicious devices which is achieved by analyzing the unique physical and/or operational characteristics of IoT devices. In the era of the latest progress in machine learning, particularly generative models, it is crucial to methodically examine the current studies in device fingerprinting. This involves explaining their approaches and underscoring their limitations when faced with adversaries armed with these ML tools. To systematically analyze existing methods, we propose a generic, yet simplified, model for device fingerprinting. Additionally, we thoroughly investigate existing methods to authenticate devices and detect eavesdropping, using our proposed model. We further study trends and similarities between works in authentication and eavesdropping detection and present the existing threats and attacks in these domains. Finally, we discuss future directions in fingerprinting based on these trends to develop more secure IoT fingerprinting schemes.

Other2 citations2025-01-01Paper ->

Security Helper Chiplets: A New Paradigm for Secure Hardware Monitoring

Pooya Aghanoury, Santosh Ghosh, Nader Sehatbakhsh

Hardware-assisted security features are a powerful tool for safeguarding computing systems against various attacks. However, integrating hardware security features (HWSFs) within complex System-on-Chip (SoC) architectures often leads to scalability issues and/or resource competition, impacting metrics such as area and power, ultimately leading to an undesirable trade-off between security and performance. In this study, we propose re-evaluating HWSF design constraints in light of the recent paradigm shift from integrated SoCs to chiplet-based architectures. Specifically, we explore the possibility of leveraging a centralized and versatile security module based on chiplets called security helper chiplets. We study the cost implications of using such a model by developing a new framework for cost analysis. Our analysis highlights the cost tradeoffs across different design strategies.

Learning0 citations2025-01-01Paper ->

Secure artificial intelligence at the edge

Nader Sehatbakhsh, S. Pamarti, Vwani Roychowdhary, Subramanian Iyer

Sensors for the perception of multimodal stimuli—ranging from the five senses humans possess and beyond—have reached an unprecedented level of sophistication and miniaturization, raising the prospect of making man-made large-scale complex systems that can rival nature a reality. Artificial intelligence (AI) at the edge aims to integrate such sensors with real-time cognitive abilities enabled by recent advances in AI. Such AI progress has only been achieved by using massive computing power which, however, would not be available in most distributed systems of interest. Nature has solved this problem by integrating computing, memory and sensing functionalities in the same hardware so that each part can learn its environment in real time and take local actions that lead to stable global functionalities. While this is a challenging task by itself, it would raise a new set of security challenges when implemented. As in nature, malicious agents can attack and commandeer the system to perform their own tasks. This article aims to define the types of systemic attacks that would emerge, and introduces a multiscale framework for combatting them. A primary thesis is that edge AI systems have to deal with unknown attack strategies that can only be countered in real time using low-touch adaptive learning systems. This article is part of the theme issue ‘Emerging technologies for future secure computing platforms’.

Other3 citations2025Paper ->

Chimera: Creating Digitally Signed Fake Photos by Fooling Image Recapture and Deepfake Detectors

Seongbin Park, Alexander Vilesov, Jinghui Zhang, Hossein Khalili, Yuan Tian et al.

Learning4 citations2024-11-02Paper ->

SRC: Sustainable Reactive Computing for Battery-free Edge Intelligence

Sepehr Tabrizchi, Nedasadat Taheri, Justin Feng, Nader Sehatbakhsh, David Z. Pan et al.

This paper proposes SRC, a novel framework for efficient and reliable inference on battery-free smart Internet of Things (IoT) devices. SRC supports various configurations that follow reactive configuration while using the innovative state machine and a safe threshold mechanism to proactively halt operations, reducing store/load operations by up to 75%. It strategically stores essential convolutional neural network (CNN) data (layer, kernel, etc.) to optimize input/output feature map management. This reactive design allows seamless task resumption across power cycles, ensuring continuity in unpredictable energy environments. Experiments show significant gains, with SRC achieving on average ~ 81.85% reduction in read/write operations and approximately 57.18% improvement in sensing compared to conventional reactive methods based on the intermittent Energy Trace 1.

Robotics0 citations2024-08-31arXiv ->

LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models

Hossein Khalili, Seongbin Park, Vincent Li, Brandan Bright, Ali Payani et al.

Autonomous mobile systems increasingly rely on deep neural networks for perception and decision-making. While effective, these systems are vulnerable to adversarial machine learning attacks where small perturbations in the input could significantly impact the outcome of the system. Common countermeasures include leveraging adversarial training and/or data or network transformation. Although widely used, the main drawback of these countermeasures is that they require full and invasive access to the classifiers, which are typically proprietary. Additionally, the cost of training or retraining is often prohibitively expensive for large models. To tackle this, purification models have recently been proposed. The aim is to incorporate a "purification" layer before classification, thereby eliminating the necessity to modify the classifier. Despite their effectiveness, state-of-the-art purification methods are compute-intensive, rendering them unsuitable for mobile systems where resources are constrained and large latency is not desired. This paper presents a new approach, LightPure, that enhances the purification of adversarial images. It improves the accuracy of the current leading purification methods while also providing notable enhancements in speed and computational efficiency, making it suitable for mobile devices with limited resources. Our approach uses a two-step diffusion and one-shot Generative Adversarial Network (GAN) framework for purification, prioritizing latency without compromising robustness. We propose several new techniques in designing our model to achieve a reasonable balance between classification accuracy and adversarial robustness while maintaining a desired latency. We design and implement a proof-of-concept on a Jetson Nano board and evaluate our method using several attack scenarios and datasets. Our results show that LightPure can outperform existing purification methods by up to 10x in terms of latency while achieving higher accuracy and robustness for various black-, gray-, and white-box attack scenarios. The fusion of speed and robust defense mechanisms positions our method as a significant advancement in the field of adversarial image purification, offering a scalable and effective solution for real-world mobile systems.

Learning0 citations2024-07-04arXiv ->

Solutions to Deepfakes: Can Camera Hardware, Cryptography, and Deep Learning Verify Real Images?

Alexander Vilesov, Yuan Tian, Nader Sehatbakhsh, Achuta Kadambi

The exponential progress in generative AI poses serious implications for the credibility of all real images and videos. There will exist a point in the future where 1) digital content produced by generative AI will be indistinguishable from those created by cameras, 2) high-quality generative algorithms will be accessible to anyone, and 3) the ratio of all synthetic to real images will be large. It is imperative to establish methods that can separate real data from synthetic data with high confidence. We define real images as those that were produced by the camera hardware, capturing a real-world scene. Any synthetic generation of an image or alteration of a real image through generative AI or computer graphics techniques is labeled as a synthetic image. To this end, this document aims to: present known strategies in detection and cryptography that can be employed to verify which images are real, weight the strengths and weaknesses of these strategies, and suggest additional improvements to alleviate shortcomings.

MPC/Planning2 citations2024-06-12Paper ->

SCRIPT: A Multi-Objective Routing Framework for Securing Chiplet Systems against Distributed DoS Attacks

Ebadollah Taheri, Pooya Aghanoury, S. Pasricha, Mahdi Nikdast, Nader Sehatbakhsh

Heterogeneous 2.5D integration enables seamless integration of chiplets, hence reducing design time and costs. Concerns arise when dealing with untrustworthy chiplets, emphasizing the need for dependable Network-on-Interposer (NoI). This paper introduces SCRIPT, a secure routing framework to mitigate Distributed Denial-of-Service (DDoS) attacks in chiplet systems. SCRIPT obscures predictable paths exploited by attackers, disrupting orchestrated attacks. SCRIPT considers chiplet trust and criticality and employs a multi-objective optimization technique to enhance NoI performance and reliability. Evaluations show that SCRIPT enhances NoI security by at least 64% against DDoS attacks.

MPC/Planning0 citations2024-06-03Paper ->

RefreshChannels: Exploiting Dynamic Refresh Rate Switching for Mobile Device Attacks

Gaofeng Dong, Jason Wu, Julian de Gortari Briseno, Akash Deep Singh, Justin Feng et al.

Mobile devices with dynamic refresh rate (DRR) switching displays have recently become increasingly common. For power optimization, these devices switch to lower refresh rates when idling, and switch to higher refresh rates when the content displayed requires smoother transitions. However, the security and privacy vulnerabilities of DRR switching have not been investigated properly. In this paper, we propose a novel attack vector called RefreshChannels that exploits DRR switching capabilities for mobile device attacks. Specifically, we first create a covert channel between two colluding apps that are able to stealthily share users' private information by modulating the data with the refresh rates, bypassing the OS sandboxing and isolation measures. Second, we further extend its applicability by creating a covert channel between a malicious app and either a phishing webpage or a malicious advertisement on a benign webpage. Our extensive evaluations on five popular mobile devices from four different vendors demonstrate the effectiveness and widespread impacts of these attacks. Finally, we investigate several countermeasures, such as restricting access to refresh rates, and find they are inadequate for thwarting RefreshChannels due to DDR's unique characteristics.

Other5 citations2024-05-23Paper ->

Virtual Keymysteries Unveiled: Detecting Keystrokes in VR with External Side-Channels

Hossein Khalili, Alexander Chen, Theodoros Papaiakovou, Timothy Jacques, Hao-Jen Chien et al.

AR/VR devices are becoming prevalent, permeating different facets of our daily lives. Nevertheless, this prevalence presents fresh security and privacy hurdles as users increasingly employ these devices to manage sensitive data such as passwords, personal information, and financial data in potentially insecure settings. Due to these concerns, there has been an increasing trend in the literature to analyze security and privacy threats for AR/VR by proposing novel attack strategies. While effective and worrisome, the existing body of work has focused mostly on internal threats for AR/VR devices, such as malicious sensors, apps, or firmware. However, in this paper, we focus on a new facet of this body of research by designing an external attacker. The key observation is that although the virtual world remains concealed from an external observer (i.e., an adversary), the physical interactions required to input commands into the VR world are observable and create a side channel. Building upon this finding, we conduct a practical attack, named LensHack, on Quest 2 VR devices. By employing our algorithm and an external camera (Blink), we capture and analyze the interactions between the user and the device, successfully extracting typed characters with over 80% accuracy.

CBF Related Papers
Robotics0 citations2021-09-25arXiv ->

Safety-Critical Control and Planning for Obstacle Avoidance between Polytopes with Control Barrier Functions

A. Thirugnanam, Jun Zeng, K. Sreenath

Obstacle avoidance between polytopes is a chal-lenging topic for optimal control and optimization-based tra-jectory planning problems. Existing work either solves this problem through mixed-integer optimization, relying on simpli-fication of system dynamics, or through model predictive control with dual variables using distance constraints, requiring long horizons for obstacle avoidance. In either case, the solution can only be applied as an offline planning algorithm. In this paper, we exploit the property that a smaller horizon is sufficient for obstacle avoidance by using discrete-time control barrier function (DCBF) constraints and we propose a novel optimization formulation with dual variables based on DCBFs to generate a collision-free dynamically-feasible trajectory. The proposed optimization formulation has lower computational complexity compared to existing work and can be used as a fast online algorithm for control and planning for general nonlinear dynamical systems. We validate our algorithm on different robot shapes using numerical simulations with a kinematic bicycle model, resulting in successful navigation through maze environments with polytopic obstacles.

Robotics0 citations2020-07-22arXiv ->

Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Function

Jun Zeng, Bike Zhang, K. Sreenath

The optimal performance of robotic systems is usually achieved near the limit of state and input bounds. Model predictive control (MPC) is a prevalent strategy to handle these operational constraints, however, safety still remains an open challenge for MPC as it needs to guarantee that the system stays within an invariant set. In order to obtain safe optimal performance in the context of set invariance, we present a safety-critical model predictive control strategy utilizing discrete-time control barrier functions (CBFs), which guarantees system safety and accomplishes optimal performance via model predictive control. We analyze the feasibility and the stability properties of our control design. We verify the properties of our method on a 2D double integrator model for obstacle avoidance. We also validate the algorithm numerically using a competitive car racing example, where the ego car is able to overtake other racing cars.

CBF Related Papers
Theory0 citations2025-01-07arXiv ->

Proxy Control Barrier Functions: Integrating Barrier-Based and Lyapunov-Based Safety-Critical Control Design

Yujie Wang, Xiangru Xu

This work introduces a novel Proxy Control Barrier Function (PCBF) scheme that integrates barrier-based and Lyapunov-based safety-critical control strategies for strict-feedback systems with potentially unknown dynamics. The proposed method employs a modular design procedure, decomposing the original system into a proxy subsystem and a virtual tracking subsystem that are controlled by the control barrier function (CBF)-based and Lyapunov-based controllers, respectively. By integrating these separately designed controllers, the overall system's safety is ensured. Moreover, a new filter-based disturbance observer is utilized to design a PCBF-based safe controller for strict-feedback systems subject to mismatched disturbances. This approach broadens the class of systems to which CBF-based methods can be applied and significantly simplifies CBF construction by requiring only the model of the proxy subsystem. The effectiveness of the proposed method is demonstrated through numerical simulations.

Theory0 citations2023-09-13arXiv ->

Immersion and Invariance-Based Disturbance Observer and Its Application to Safe Control

Yujie Wang, Xiangru Xu

When the disturbance input matrix is nonlinear, existing disturbance observer design methods rely on the solvability of a partial differential equation or the existence of an output function with a uniformly well-defined disturbance relative degree, which can pose significant limitations. This note introduces a systematic approach for designing an immersion and invariance-based disturbance observer (IIDOB) that circumvents these strong assumptions. The proposed IIDOB ensures the disturbance estimation error is globally uniformly ultimately bounded by approximately solving a partial differential equation while compensating for the approximation error. Furthermore, by integrating IIDOB into the framework of control barrier functions, a filter-based safe control design method for control-affine systems with disturbances is established, where the filter is used to generate an alternative disturbance estimation signal with a known derivative. Sufficient conditions are established to guarantee the safety of the disturbed systems. Simulation results demonstrate the effectiveness of the proposed method.

Learning0 citations2023-09-09arXiv ->

Safe Control of Euler-Lagrange Systems with Limited Model Information

Yujie Wang, Xiangru Xu

This work presents a new safe control framework for Euler-Lagrange (EL) systems with limited model information, external disturbances, and measurement uncertainties. The EL system is decomposed into two subsystems called the proxy subsystem and the virtual tracking subsystem. An adaptive safe controller based on barrier Lyapunov functions is designed for the virtual tracking subsystem to ensure the boundedness of the safe velocity tracking error, and a safe controller based on control barrier functions is designed for the proxy subsystem to ensure controlled invariance of the safe set defined either in the joint space or task space. Theorems that guarantee the safety of the proposed controllers are provided. In contrast to existing safe control strategies for EL systems, the proposed method requires much less model information and can ensure safety rather than input-to-state safety. Simulation results are provided to illustrate the effectiveness of the proposed method.

Learning0 citations2023-02-16arXiv ->

Adaptive Safety-Critical Control for a Class of Nonlinear Systems with Parametric Uncertainties: A Control Barrier Function Approach

Yujie Wang, Xiangru Xu

This paper presents a novel approach for the safe control design of systems with parametric uncertainties in both drift terms and control-input matrices. The method combines control barrier functions and adaptive laws to generate a safe controller through a nonlinear program with an explicitly given closed-form solution. The proposed approach verifies the non-emptiness of the admissible control set independently of online parameter estimations, which can ensure the safe controller is singularity-free. A data-driven algorithm is also developed to improve the performance of the proposed controller by tightening the bounds of the unknown parameters. The effectiveness of the control scheme is demonstrated through numerical simulations.

Other0 citations2022-03-24arXiv ->

Disturbance Observer-based Robust Control Barrier Functions

Yujie Wang, Xiangru Xu

This work presents a safe control design approach that integrates the disturbance observer (DOB) and the control barrier function (CBF) for systems with external disturbances. Different from existing robust CBF results that consider the "worst case" of disturbances, this work utilizes a DOB to estimate and compensate for the disturbances. DOB-CBF-based controllers are constructed with provably safe guarantees by solving convex quadratic programs online, to achieve a better tradeoff between safety and performance. Two types of systems are considered individually depending on the magnitude of the input and disturbance relative degrees. The effectiveness of the proposed methods is illustrated via numerical simulations.

MPC/Planning0 citations2021-11-01arXiv ->

Flatness-Based Quadcopter Trajectory Planning and Tracking With Continuous-Time Safety Guarantees

Victor Freire, Xiangru Xu

This work proposes a convex optimization-based framework for the trajectory planning and tracking of quadcopters that ensures continuous-time safety guarantees. Using the convexity property of B-spline curves and the differential flatness property of quadcopters, a second-order cone program is formulated to generate an optimal nominal trajectory that respects state and input constraints, including position, linear velocity, angle, angular velocity, thrust, waypoints, and obstacle avoidance constraints, rigorously in the continuous-time sense. To ensure safe trajectory tracking, a convex quadratic program is proposed based on control barrier functions, which guarantees that the actual trajectory of the quadcopter remains within a prescribed safe tube of the nominal trajectory in continuous time. Furthermore, conditions that ensure the safe tracking controller respects thrust, roll, and pitch constraints are also presented. Both the planning and control approaches are suitable for online implementation, and the effectiveness of the proposed framework is demonstrated through simulations and experiments with a Crazyflie2.1 nano quadcopter.

Learning0 citations2021-10-03arXiv ->

Observer-based Control Barrier Functions for Safety Critical Systems

Yujie Wang, Xiangru Xu

This paper considers the safety-critical control design problem with output measurements. An observer-based safety control framework that integrates the estimation error quantified observer and the control barrier function (CBF) approach is proposed. The function approximation technique is employed to approximate the uncertainties introduced by the state estimation error, and an adaptive CBF approach is proposed to design the safe controller which is obtained by solving a convex quadratic program (QP). Theoretical results for CBFs with a relative degree 1 and a higher relative degree are given individually. The effectiveness of the proposed control approach is demonstrated by two numerical examples.

MPC/Planning0 citations2021-10-03arXiv ->

Control Barrier Function Meets Interval Analysis: Safety-Critical Control with Measurement and Actuation Uncertainties

Yuhao Zhang, Sequoyah Walters, Xiangru Xu

This paper presents a framework for designing provably safe feedback controllers for sampled-data control affine systems with measurement and actuation uncertainties. Based on the interval Taylor model of nonlinear functions, a sampled-data control barrier function (CBF) condition is proposed which ensures the forward invariance of a safe set for sampled-data systems. ℝeachable set overapproximation and Lasserre’s hierarchy of polynomial optimization are used for finding a margin term in the sampled-data CBF condition. Sufficient conditions for a safe controller in the presence of measurement and actuation uncertainties are proposed. The effectiveness of the proposed method is illustrated by a numerical example and an experimental example that implements the proposed controller on the Crazyflie quadcopter in real-time.

MPC/Planning0 citations2016-12-05arXiv ->

Robustness of Control Barrier Functions for Safety Critical Control

Xiangru Xu, P. Tabuada, J. Grizzle, A. Ames

Abstract Barrier functions (also called certificates) have been an important tool for the verification of hybrid systems, and have also played important roles in optimization and multi-objective control. The extension of a barrier function to a controlled system results in a control barrier function. This can be thought of as being analogous to how Sontag extended Lyapunov functions to control Lypaunov functions in order to enable controller synthesis for stabilization tasks. A control barrier function enables controller synthesis for safety requirements specified by forward invariance of a set using a Lyapunov-like condition. This paper develops several important extensions to the notion of a control barrier function. The first involves robustness under perturbations to the vector field defining the system. Input-to-State stability conditions are given that provide for forward invariance, when disturbances are present, of a “relaxation” of set rendered invariant without disturbances. A control barrier function can be combined with a control Lyapunov function in a quadratic program to achieve a control objective subject to safety guarantees. The second result of the paper gives conditions for the control law obtained by solving the quadratic program to be Lipschitz continuous and therefore to gives rise to well-defined solutions of the resulting closed-loop system.

MPC/Planning0 citations2016-09-22arXiv ->

Correctness Guarantees for the Composition of Lane Keeping and Adaptive Cruise Control

Xiangru Xu, J. Grizzle, P. Tabuada, A. Ames

This paper develops a control approach with correctness guarantees for the simultaneous operation of lane keeping and adaptive cruise control. The safety specifications for these driver assistance modules are expressed in terms of set invariance. Control barrier functions (CBFs) are used to design a family of control solutions that guarantee the forward invariance of a set, which implies satisfaction of the safety specifications. The CBFs are synthesized through a combination of sum-of-squares program and physics-based modeling and optimization. A real-time quadratic program is posed to combine the CBFs with the performance-based controllers, which can be either expressed as control Lyapunov function conditions or as black-box legacy controllers. In both cases, the resulting feedback control guarantees the safety of the composed driver assistance modules in a formally correct manner. Importantly, the quadratic program admits a closed-form solution that can be easily implemented. The effectiveness of the control approach is demonstrated by simulations in the industry-standard vehicle simulator Carsim. Note to Practitioners—Safety is of paramount importance for the control of automated vehicles. This paper is motivated by the problem of designing controllers that are provably correct for the simultaneous operation of two driver assistance modules, lane keeping and adaptive cruise control. This is a challenging problem partially, because the lateral and longitudinal dynamics of the vehicles are coupled, with few results known to exist that provide formal guarantees. In this paper, we employ an assume-guarantee formalism between these two subsystems, such that they can be considered individually; based on that, we use optimization to design safe sets that serves as “supervisors” for vehicle behavior, such that the trajectories of the closed-loop system are confined within the safe sets using predetermined bounds on wheel force and steering angle. The feedback controller is constructed by solving convex quadratic programs online, which can also be given in closed form, making the implementation much easier. One particular advantage of this control approach is that the safety set and the performance controller can be designed separately, which enables the integration of a legacy controller into a correct-by-construction solution.

MPC/Planning2673 citations2016-09-21arXiv ->

Control Barrier Function Based Quadratic Programs for Safety Critical Systems

A. Ames, Xiangru Xu, J. Grizzle, P. Tabuada

Safety critical systems involve the tight coupling between potentially conflicting control objectives and safety constraints. As a means of creating a formal framework for controlling systems of this form, and with a view toward automotive applications, this paper develops a methodology that allows safety conditions—expressed as control barrier functions—to be unified with performance objectives—expressed as control Lyapunov functions—in the context of real-time optimization-based controllers. Safety conditions are specified in terms of forward invariance of a set, and are verified via two novel generalizations of barrier functions; in each case, the existence of a barrier function satisfying Lyapunov-like conditions implies forward invariance of the set, and the relationship between these two classes of barrier functions is characterized. In addition, each of these formulations yields a notion of control barrier function (CBF), providing inequality constraints in the control input that, when satisfied, again imply forward invariance of the set. Through these constructions, CBFs can naturally be unified with control Lyapunov functions (CLFs) in the context of a quadratic program (QP); this allows for the achievement of control objectives (represented by CLFs) subject to conditions on the admissible states of the system (represented by CBFs). The mediation of safety and performance through a QP is demonstrated on adaptive cruise control and lane keeping, two automotive control problems that present both safety and performance considerations coupled with actuator bounds.

Other27 citations2016-09-21Paper ->

Control Barrier Function Based Quadratic Programs with Application to Automotive Safety Systems

A. Ames, Xiangru Xu, J. Grizzle, P. Tabuada

Robotics239 citations2015-07-01Paper ->

Control barrier function based quadratic programs with application to bipedal robotic walking

Shao-Chen Hsu, Xiangru Xu, A. Ames

Non-CBF Papers
Other3 citations2026-03-01Paper ->

Advances and prospects of closed-loop precision irrigation for synergistic water-salt-phosphorus regulation in saline-alkali soils

L. Huang, Shuke Zheng, Mostafa Elshobary, Tengfei Li, Wei Liu et al.

Learning0 citations2025-12-17arXiv ->

From Risk to Resilience: Towards Assessing and Mitigating the Risk of Data Reconstruction Attacks in Federated Learning

Xiangru Xu, Zhize Li, Yufei Han, Bin Wang, Jiqiang Liu et al.

Data Reconstruction Attacks (DRA) pose a significant threat to Federated Learning (FL) systems by enabling adversaries to infer sensitive training data from local clients. Despite extensive research, the question of how to characterize and assess the risk of DRAs in FL systems remains unresolved due to the lack of a theoretically-grounded risk quantification framework. In this work, we address this gap by introducing Invertibility Loss (InvLoss) to quantify the maximum achievable effectiveness of DRAs for a given data instance and FL model. We derive a tight and computable upper bound for InvLoss and explore its implications from three perspectives. First, we show that DRA risk is governed by the spectral properties of the Jacobian matrix of exchanged model updates or feature embeddings, providing a unified explanation for the effectiveness of defense methods. Second, we develop InvRE, an InvLoss-based DRA risk estimator that offers attack method-agnostic, comprehensive risk evaluation across data instances and model architectures. Third, we propose two adaptive noise perturbation defenses that enhance FL privacy without harming classification accuracy. Extensive experiments on real-world datasets validate our framework, demonstrating its potential for systematic DRA risk evaluation and mitigation in FL systems.

Other2 citations2025-09-09Paper ->

Combined Fusarium Crown Rot and Drought Stress Leads to Overlapping and Unique Proteomic Responses in Wheat.

Yutian Gao, Jingjing Jin, Hongyao Lou, Shuonan Duan, Xiaohan Zhou et al.

Other10 citations2025-07-02Paper ->

Integrated hybrid Nested-bottled photobioreactor for enhanced mixing, mass transfer, and CO₂ fixation in Arthrospira platensis raceway pond cultivation systems

A. A. Kubar, Shahid Mehmood, Michael Schagerl, Santosh Kumar, Xinjuan Hu et al.

This study introduces a novel hybrid photobioreactor system that integrates an open raceway pond (ORWP) with a Nested-bottled photobioreactor (NB-PBR) in a closed-loop configuration to enhance microalgal biomass production and CO₂ fixation. The system facilitates continuous culture circulation, improving mass transfer and mixing efficiency while ensuring optimal light exposure and CO₂ dissolution. This design resulted in a 38% increase in dry mass (3.1 g/L) and improved mass transfer and mixing times by 16.6% and 15.3%, respectively. The optimized cultivation conditions led to a 39.9% enhancement in CO₂ fixation and an 8.7% increase in photosynthetic efficiency (Fv/Fm) compared to traditional systems. The strategic movement of poorly illuminated ORWP to the NB-PBR maximized light absorption and nutrient uptake, significantly boosting overall productivity. These findings highlight the potential of hybrid photobioreactor systems in improving microalgal growth efficiency and advancing sustainable algal cultivation for commercial applications.

Biomedical3 citations2025-04-25Paper ->

Chronic chlorothalonil exposure inhibits locomotion and interferes with the gut-liver axis in Pelophylax nigromaculatus tadpoles

Minyi Huang, Yuhao Zhang, Xiangru Xu, Renyan Duan, Hui Yang

Chlorothalonil is a widely used fungicide that has a negative effect on individual movement, but its impact pathway needs further refinement. Here, the effects of exposure to chlorothalonil on the locomotion behavior of Pelophylax nigromaculatus tadpoles (GS23) were measured at three different levels (0 µg/L, 10 µg/L, and 50 µg/L), and the possible pathways of its effects were analyzed from the gut-liver axis. Chlorothalonil exposure levels of 10 µg/L and 50 µg/L significantly reduced the average speed of P. nigromaculatus tadpoles by 26% and 32.7%, respectively, and significantly decreased the locomotor frequency by 27.1% and 58.6%, respectively. Gut microbiota analysis revealed chlorothalonil exposure significantly increased the abundance of Firmicutes, while significantly decreased the abundance of Actinobacteriota, Pseudomonas, and Rhodococcus. Metabolomics analysis identified that chlorothalonil treatment changed amino acid-related metabolism pathways in the gut and liver and altered the glycerophospholipid metabolism pathway in the liver. This study indicated that chlorothalonil can affect individual locomotor abilities and interfering with the gut-liver axis of aquatic animals. These findings establish that chlorothalonil compromises aquatic organism motility through a multi-target mechanism involving gut microbiota modulation, amino acid metabolic interference, and hepatic lipid pathway disruption.

Other12 citations2025-04-01Paper ->

Colorimetric films of carboxymethyl cellulose and sodium alginate incorporating Spirulina extract (phycobiliproteins) and gallic acid for real-time shrimp freshness monitoring.

Dr. Muhammad Abdur Rehman Shah, Yajie Zhang, O. Rehman, Feifei Zhu, Santosh Kumar et al.

This study developed edible colorimetric films by incorporating 1 % ultrasonic-assisted aqueous extract of Spirulina platensis (UAAESP; 76.83 % protein), and 0.125-0.250 % gallic acid (GA) into 2 % carboxymethyl cellulose (CMC) and sodium alginate (SA) matrices. The films were evaluated for structural, optical, mechanical, antimicrobial, antioxidant, and calorimetric properties. UAAESP exhibited a blue-grey colour at pH 3-9 and yellowish-green at pH 10, reflecting higher UV-visible absorption. The addition of 1 % UAAESP and 0.25 % GA reduced moisture content (7.73 %), water solubility (12.06 %), and water vapor and oxygen permeability, while increasing film thickness (10.97 %) and tensile strength (38.53 %). Film opacity increased due to the blue colour of UAAESP. SEM showed homogeneous surfaces, with minor cracks in cross-sections, while FTIR confirmed strong physical interactions between CMC, SA, UAAESP, and GA. Antioxidant activity improved with UAAESP and higher GA levels, while 0.25 % GA expanded inhibition zones by 74.25 % and 81.09 % against S. aureus and E. coli. The GA not only improve the antioxidant and antimicrobial activities but also sensitize the UAAESP incorporated in the matrices to better sense the spoilage levels. The films' colour changes (blue, bluish-grey, dark grey) corresponded shrimp spoilage levels. Thus, UAAESP-GA films offer real-time freshness indicators and sustainable, recyclable alternatives to plastic packaging.

Learning14 citations2025-03-01Paper ->

Finding the PISTE: Towards Understanding Privacy Leaks in Vertical Federated Learning Systems

Xiangru Xu, Wei Wang, Zheng Chen, Bin Wang, Chao Li et al.

Vertical Federated Learning (VFL) is a collaborative learning paradigm where participants share the same sample space while splitting the feature space. In VFL, local participants host their bottom models for feature extraction and collaboratively train a classifier by exchanging intermediate results with the server owning the labels. Both local training data and bottom models contain privacy-sensitive information and are considered the intellectual property of each participant, and thus should be protected by the design of VFL. Our study exposes the fundamental susceptibility of VFL systems to privacy leaks, which arise from the collaboration between the server and clients during both training and testing. Based on our findings, we propose PISTE, a model-agnostic framework of privacy stealing attacks against VFL. PISTE delivers three privacy inference attacks, i.e., model stealing, data reconstruction, and property inference attacks on five benchmark datasets and four different model architectures. We further discuss four potential countermeasures. Experimental results show that all of them cannot prevent all three privacy stealing attacks in PISTE. In summary, our study demonstrates the inherent yet rarely uncovered vulnerability of VFL on leaking data and model privacy.

Learning3 citations2025-03-01Paper ->

Enhancing Privacy in Distributed Intelligent Vehicles With Information Bottleneck Theory

Xiangru Xu, Pengrui Liu, Yiwen Zhao, Lei Han, Wei Wang et al.

Vertical federated learning (VFL) shows promise for enabling collaborative learning among Internet of Vehicle systems (IoVs) without requiring the sharing of private training data. However, existing work has exposed VFL’s vulnerability to privacy-stealing attacks, where an honest but curious server might reconstruct a client’s raw data from client-uploaded embeddings. In this work, we first elucidate the intrinsic mechanisms of privacy attacks from an information theory perspective, which provides a solid foundation for potential defensive strategies. Based on our findings, we introduce PriVFL, a defense mechanism based on information bottleneck theory. PriVFL is designed to safeguard the privacy of VFL-based IoVs by enabling shared embeddings to extract minimal information from input data, while preserving the information essential to target labels. Specifically, PriVFL restricts the information contained in embeddings by reducing the upper bound of mutual information between the raw samples and embeddings uploaded from local clients. Meanwhile, PriVFL ensures the effectiveness of the model by increasing the mutual information lower bound between embeddings and samples’ labels. Our evaluation includes 5 benchmark data sets and 4 different models. Experimental results demonstrate that PriVFL effectively mitigates privacy attacks while preserving the model’s effectiveness. These findings underscore that PriVFL can significantly enhance the privacy of VFL-based IoVs, thereby bolstering the development of practical IoV applications.

Learning3 citations2025-03-01Paper ->

DMRP: Privacy-Preserving Deep Learning Model with Dynamic Masking and Random Permutation

Chongzhen Zhang, Zhi Hu, Xiangru Xu, Yong Liu, Bin Wang et al.

Other6 citations2025-02-01Paper ->

On converse zeroing barrier functions

Ziliang Lyu, Xiangru Xu, Yiguang Hong, Lihua Xie

Other12 citations2025-01-01Paper ->

Identification of genetic loci and candidate genes underlying Fusarium crown rot resistance in wheat

Yuqing Su, Xiangru Xu, Yunqiao Wang, Tongzhu Wang, Jiazheng Yu et al.

Other9 citations2024-12-01Paper ->

Analysis of Microbial Diversity Dominating Nitrite Enzymatic Degradation and Acidic Degradation in the Fermentation Broth of Northeast Sauerkraut

Xiangru Xu, Meng Zhang, Yu Tao, Wei Wei

Nitrite hazard is an important food safety issue in the production process of Chinese Northeastern sauerkraut, but this nitrite can be eliminated through microbial enzymatic degradation and acidic degradation as fermentation progresses. Therefore, analyzing the microbial diversity that dominates nitrite degradation in Chinese Northeastern sauerkraut can provide a reference for its safe production. In this study, based on the dynamic monitoring of nitrite concentration, pH, and the abundance of nitrite reductase genes (nirK and nirS) and the application of high-throughput sequencing technology and various statistical analysis methods, the microbial groups associated with nitrite enzymatic degradation and acidic degradation in Northeast sauerkraut fermentation broth were analyzed. During the nitrite peak period of Northeast sauerkraut fermentation broth, the nitrite concentration reached 32.15 mg/kg, the pH was 4.7, and the abundances of the nitrite reductase genes nirK and nirS were 3.0 × 104 and 4.9 × 104 copies/μL, respectively. At this stage, nitrite degradation was likely dominated by enzymatic activities. Microbial phyla such as Bacteroidetes (38.8%), Proteobacteria (19.2%), and the archaeal phylum Euryarchaeota (1.1%) showed strong correlations with nitrite. Among the genera within these three phyla, Chryseobacterium, Elizabethkingia, and Aeromonas exhibited significant differences in abundance compared to the late fermentation stage and were identified as the primary microbial groups likely driving the enzymatic degradation. During the nitrite degradation period, the nitrite concentration decreased to 0.04 mg/kg, the pH dropped to 3.6, and the abundances of nirK and nirS genes were reduced to 1.0 × 103 copies/μL. At this stage, the nitrite degradation was primarily driven by acid activity. The bacterial phylum Firmicutes (99%) exhibited a strong correlation with pH. Within this phylum, the genus Lactobacillus, which showed significant differences in abundance compared to the early fermentation stage, was identified as the primary microbial group indirectly contributing to acidic degradation. This study provides guidance for the isolation of food-grade prokaryotic microbial strains capable of nitrite degradation. Additionally, the findings offer a methodological reference for conducting future research on nitrite-degrading microorganisms in fermented vegetable broths.

Theory8 citations2024-11-17Paper ->

A Model-Driven Approach to Extract Multi-Source Fault Features of a Screw Pump

Weigang Wen, Jingqi Qin, Xiangru Xu, Kaifu Mi, Meng Zhou

Screw pumps’ faulty working conditions affect the stability of oil production. At project sites, different sensors are used simultaneously to collect multi-dimensional signals; the data fault labels and location are not clear, and how to comprehensively use multi-source information in effective fault feature extraction has become an urgent issue. Existing diagnostic methods use a single signal or part of a signal and do not fully utilize the acquired signal, which makes it difficult to achieve the required accuracy of diagnostic results. This paper focuses on the model-driven approach to extract multi-source fault features of screw pumps. Firstly, it constructs a fault data model (FDM) by analyzing the fault mechanism of the screw pump. Secondly, it uses the FDM to select an effective data set. Thirdly, it constructs a multi-dimensional fault feature extraction model (MDFEM) to extract featured signal features and data features, for which we also comprehensively used multi-source signals in effective fault feature extraction, while other traditional methods only use one or two signals. Finally, after feature selection, unsupervised fault diagnosis was achieved by using the k-means method. After experimental verification, the method can comprehensively use multi-source information to construct an effective data set and extract multi-dimensional, effective fault features for screw pump fault diagnosis.

Other5 citations2024-11-15Paper ->

Assessing Membership Leakages via Task-Aligned Divergent Shadow Data Sets in Vehicular Road Cooperation

Pengrui Liu, Wei Wang, Xiangru Xu, Hanxi Li, Weiping Ding

Deep classification models have been widely utilized in vehicular road cooperation. However, previous work indicates that deep classification models are vulnerable to the privacy risks of membership inference attacks (MIAs). Most existing work of MIAs is based on two different assumptions. One assumes adversary-own shadow data sets with aligned tasks and distributions as private data sets, while this assumption necessitates that the adversary knows the distributions of private data sets. The other assumes adversary-own shadow data sets with distinct tasks and distributions from private data sets, while this assumption requires that the adversary knows the classification boundary between members and nonmembers of the private data set. Hence, these two assumptions do not always hold in real-world scenarios. In this work, we systematically assess the impact of adversary-own shadow data sets with aligned tasks but distinct distributions from private data sets on MIAs. These realistic shadow data sets acknowledge adversaries’ limited insights into the data distribution of the private data set and the decision boundary between members and nonmembers. We divide these practical shadow data sets hosted by adversaries into four types: Data Noise, Label Noise, Imbalanced Data, and Cross-domain Data. We conduct extensive experiments with seven prevalent MIAs and four types of shadow data sets. Experimental results mainly reveal twofold findings. First, MIAs still maintain effectiveness using the shadow data set with the aligned task but distinct distribution from the private data set. Second, different levels of data distribution disparities manifest varying MIAs’ performances under certain types of shadow data sets.

Other3 citations2024-09-01Paper ->

Prediction strategy for screening functional Haloarchaea strains with qPCR assays.

Xinyu Hu, Wen Sun, Meng Zhang, Wenjun Guo, Shujing Yang et al.

As an extremophile resource, functional Haloarchaea strains are extremely time-consuming to screen. Here, taking the screening of low-salt-tolerant strains as an example, based on the qPCR assays that shortened time by 4-7 times and achieved 100 % accuracy, a universal strategy for rapid and accurate screening of functional Haloarchaea strains was established.

Other8 citations2024-08-24Paper ->

A MYB family transcription factor TdRCA1 from wild emmer wheat regulates anthocyanin biosynthesis in coleoptile

Jinlong Li, Chaozhong Zhang, Xiangru Xu, Yuqing Su, Yutian Gao et al.

Other12 citations2024-07-11Paper ->

Does the Daily Light Integral Influence the Sowing Density of Tomato Plug Seedlings in a Controlled Environment?

Xiangru Xu, Fulin Yang, Jinxiu Song, Rong Zhang, Wei Cai

To achieve high-density tomato seedlings in a plant factory with artificial lighting, tomatoes (Solanum lycopersicum Mill. cv. “Zhongza NO.9”) were used as the experimental material. This study expected to analyze the effects of light intensity (150, 200, 250, and 300 μmol·m−2·s−1) and light time (12 and 14 h), as well as daily light integral (DLI, 10.80, 12.60, and 12.96 mol·m−2·d−1) and sowing density (50, 72, and 105 holes per tray), on seedling quality. The results indicated that biomass accumulation, seedling quality, and energy use efficiency of seedlings significantly improved with an increase in DLI. At a DLI of 12.96 mol·m−2·d−1, seedlings sown at a density of 72 holes per tray exhibited comparable growth characteristics and biomass accumulation to those sown at 50 holes per tray. However, under lower DLIs, seedlings at 50 holes per tray displayed superior growth morphology and seedling quality compared to those at 72 holes per tray. This indicates that increasing the DLI can partially mitigate the negative effects of higher sowing density on seedling quality. Light use efficiency (LUE) and energy use efficiency (EUE) were not significantly different between seedlings at 72 and 105 holes per tray but were higher than those at 50 holes per tray. Therefore, optimizing parameters such as DLI and sowing density can effectively enhance the seedling quality, spatial use efficiency, and light use efficiency in industrial seedling production. Based on the results of this study, a DLI of 12.96 mol·m−2·d−1 (achieved with a light intensity of 300 μmol·m−2·s−1 and a light time of 12 h) and sowing density of 72 holes per tray are recommended for cultivating high-quality tomato seedlings while reducing energy consumption.

Other9 citations2024-05-27Paper ->

Common Bean (Phaseolus vulgaris L.) NAC Transcriptional Factor PvNAC52 Enhances Transgenic Arabidopsis Resistance to Salt, Alkali, Osmotic, and ABA Stress by Upregulating Stress-Responsive Genes

Song Yu, Mingxu Wu, Xiaoqin Wang, Mukai Li, Xinhan Gao et al.

The NAC family of transcription factors includes no apical meristem (NAM), Arabidopsis thaliana transcription activator 1/2 (ATAF1/2), and cup-shaped cotyledon (CUC2) proteins, which are unique to plants, contributing significantly to their adaptation to environmental challenges. In the present study, we observed that the PvNAC52 protein is predominantly expressed in the cell membrane, cytoplasm, and nucleus. Overexpression of PvNAC52 in Arabidopsis strengthened plant resilience to salt, alkali, osmotic, and ABA stresses. PvNAC52 significantly (p < 0.05) reduced the degree of oxidative damage to cell membranes, proline content, and plant water loss by increasing the expression of MSD1, FSD1, CSD1, POD, PRX69, CAT, and P5CS2. Moreover, the expression of genes associated with abiotic stress responses, such as SOS1, P5S1, RD29A, NCED3, ABIs, LEAs, and DREBs, was enhanced by PvNAC52 overexpression. A yeast one-hybrid assay showed that PvNAC52 specifically binds to the cis-acting elements ABRE (abscisic acid-responsive elements, ACGTG) within the promoter. This further suggests that PvNAC52 is responsible for the transcriptional modulation of abiotic stress response genes by identifying the core sequence, ACGTG. These findings provide a theoretical foundation for the further analysis of the targeted cis-acting elements and genes downstream of PvNAC52 in the common bean.

Other26 citations2024-05-01Paper ->

Integrated partial nitrification and Tribonema minus cultivation for cost-effective ammonia recovery and lipid production from slaughterhouse wastewater

Huiying Wang, Xinjuan Hu, Mostafa E. Elshobary, Mostafa Sobhi, Feifei Zhu et al.

Other8 citations2024-05-01Paper ->

Transcriptome Analysis Reveals POD as an Important Indicator for Assessing Low-Temperature Tolerance in Maize Radicles during Germination

Yifei Zhang, Jiayu Li, Wei-Qing Li, Xinhan Gao, Xiangru Xu et al.

Low-temperature stress (TS) limits maize (Zea mays L.) seed germination and agricultural production. Exposure to TS during germination inhibits radicle growth, triggering seedling emergence disorders. Here, we aimed to analyse the changes in gene expression in the radicles of maize seeds under TS by comparing Demeiya1 (DMY1) and Zhengdan958 (ZD958) (the main Northeast China cultivars) and exposing them to two temperatures: 15 °C (control) and 5 °C (TS). TS markedly decreased radicle growth as well as fresh and dry weights while increasing proline and malondialdehyde contents in both test varieties. Under TS treatment, the expression levels of 5301 and 4894 genes were significantly different in the radicles of DMY1 and ZD958, respectively, and 3005 differentially expressed genes coexisted in the radicles of both varieties. The phenylpropanoid biosynthesis pathway was implicated within the response to TS in maize radicles, and peroxidase may be an important indicator for assessing low-temperature tolerance during maize germination. Peroxidase-encoding genes could be important candidate genes for promoting low-temperature resistance in maize germinating radicles. We believe that this study enhances the knowledge of mechanisms of response and adaptation of the maize seed germination process to TS and provides a theoretical basis for efficiently assessing maize seed low-temperature tolerance and improving maize adversity germination performance.

CBF Related Papers
MPC/Planning2673 citations2016-09-21arXiv ->

Control Barrier Function Based Quadratic Programs for Safety Critical Systems

A. Ames, Xiangru Xu, J. Grizzle, P. Tabuada

Safety critical systems involve the tight coupling between potentially conflicting control objectives and safety constraints. As a means of creating a formal framework for controlling systems of this form, and with a view toward automotive applications, this paper develops a methodology that allows safety conditions—expressed as control barrier functions—to be unified with performance objectives—expressed as control Lyapunov functions—in the context of real-time optimization-based controllers. Safety conditions are specified in terms of forward invariance of a set, and are verified via two novel generalizations of barrier functions; in each case, the existence of a barrier function satisfying Lyapunov-like conditions implies forward invariance of the set, and the relationship between these two classes of barrier functions is characterized. In addition, each of these formulations yields a notion of control barrier function (CBF), providing inequality constraints in the control input that, when satisfied, again imply forward invariance of the set. Through these constructions, CBFs can naturally be unified with control Lyapunov functions (CLFs) in the context of a quadratic program (QP); this allows for the achievement of control objectives (represented by CLFs) subject to conditions on the admissible states of the system (represented by CBFs). The mediation of safety and performance through a QP is demonstrated on adaptive cruise control and lane keeping, two automotive control problems that present both safety and performance considerations coupled with actuator bounds.

Learning1062 citations2014-12-01Paper ->

Control barrier function based quadratic programs with application to adaptive cruise control

A. Ames, J. Grizzle, P. Tabuada

CBF Related Papers
MPC/Planning0 citations2026-07-23arXiv ->

Robust Adaptive Backup Control Barrier Functions

Ersin Daş, David E. J. van Wijk, Tamas G. Molnar, Aaron D. Ames, Joel W. Burdick

We propose a notion of robust adaptive backup control barrier functions for nonlinear control affine systems with parametric uncertainty in both the drift dynamics and actuation matrix. Backup control barrier functions guarantee safety by predicting the system's trajectory under a pre-certified safe controller. However, these predictions rely on the model and can be inaccurate when the system contains unknown parameters. To address this issue, we estimate the unknown parameters using element-wise certified adaptive estimators that provide a parameter adaptation law and component-wise estimation error bounds. We compute the backup flow using the estimated model and tighten the safety conditions using these certified bounds. The resulting safety conditions account for the sensitivity of the predicted flow to parameter estimation errors. Moreover, to handle uncertainty in the actuation matrix, we use a duality-based reformulation that enables the use of a computationally efficient quadratic-program-based safety filter. We prove that controllers satisfying the proposed robust adaptive backup control barrier function constraints guarantee safety under parametric uncertainty and input constraints.

Theory0 citations2026-03-19arXiv ->

Generalizations of Backup Control Barrier Functions: Expansion and Adaptation for Input-Bounded Safety-Critical Control

David E. J. van Wijk, Dohyun Lee, Ersin Daş, T. G. Molnár, A. Ames et al.

Guaranteeing the safety of nonlinear systems with bounded inputs remains a key hurdle in safe autonomy. Backup control barrier functions (bCBFs) provide a powerful mechanism for constructing controlled invariant sets by propagating trajectories under a pre-verified backup controller to a forward invariant backup set. While effective, standard bCBFs use the same controller for both set expansion and safety certification, which can restrict the expanded safe set and lead to conservative behavior. In this study, we generalize bCBFs by separating the set-expanding controller from the verified backup controller, thereby enabling a broader class of expansion strategies while preserving formal safety guarantees. We establish sufficient conditions for forward invariance of the resulting implicit safe set and show how the generalized construction recovers existing bCBF methods as special cases. Further, we extend the proposed framework to parameterized controller families, enabling online adaptation of the expansion controller while maintaining safety guarantees in the presence of input bounds.

Other0 citations2024-09-12arXiv ->

Disturbance-Robust Backup Control Barrier Functions: Safety Under Uncertain Dynamics

David E. J. van Wijk, Samuel Coogan, T. Molnár, M. Majji, Kerianne L. Hobbs

Obtaining a controlled invariant set is crucial for safety-critical control with control barrier functions (CBFs) but is non-trivial for complex nonlinear systems and constraints. Backup control barrier functions allow such sets to be constructed online in a computationally tractable manner by examining the evolution (or flow) of the system under a known backup control law. However, for systems with unmodeled disturbances, this flow cannot be directly computed, making the current methods inadequate for assuring safety in these scenarios. To address this gap, we leverage bounds on the nominal and disturbed flow to compute a forward invariant set online by ensuring safety of an expanding norm ball tube centered around the nominal system evolution. We prove that this set results in robust control constraints which guarantee safety of the disturbed system via our Disturbance-Robust Backup Control Barrier Function (DR-bCBF) solution. The efficacy of the proposed framework is demonstrated in simulation, applied to a double integrator problem and a rigid body spacecraft rotation problem with rate constraints.

CBF Related Papers
MPC/Planning0 citations2026-07-23arXiv ->

Robust Adaptive Backup Control Barrier Functions

Ersin Daş, David E. J. van Wijk, Tamas G. Molnar, Aaron D. Ames, Joel W. Burdick

We propose a notion of robust adaptive backup control barrier functions for nonlinear control affine systems with parametric uncertainty in both the drift dynamics and actuation matrix. Backup control barrier functions guarantee safety by predicting the system's trajectory under a pre-certified safe controller. However, these predictions rely on the model and can be inaccurate when the system contains unknown parameters. To address this issue, we estimate the unknown parameters using element-wise certified adaptive estimators that provide a parameter adaptation law and component-wise estimation error bounds. We compute the backup flow using the estimated model and tighten the safety conditions using these certified bounds. The resulting safety conditions account for the sensitivity of the predicted flow to parameter estimation errors. Moreover, to handle uncertainty in the actuation matrix, we use a duality-based reformulation that enables the use of a computationally efficient quadratic-program-based safety filter. We prove that controllers satisfying the proposed robust adaptive backup control barrier function constraints guarantee safety under parametric uncertainty and input constraints.

CBF Related Papers
MPC/Planning0 citations2026-07-22arXiv ->

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

CBF Related Papers
MPC/Planning0 citations2026-07-22arXiv ->

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

CBF Related Papers
MPC/Planning0 citations2026-07-22arXiv ->

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

MPC/Planning0 citations2026-07-22arXiv ->

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

Non-CBF Papers
Other0 citationsPaper ->

Enhancing Fashion Image Generation with Attention-Based Generative Adversarial Networks

Neha Methwani, Jayant Agarwal, D. Sharma, Aniket Gupta, Deepanshu Verma et al.

Robotics0 citations2026-06-21Paper ->

"Robots should not be used for household chores because that would make us lazy": How Scaffolding Shapes Children’s Capacity to Imagine Educational Futures

Priyanka Sebastian, Sumita Sharma, N. Iivari, Marianne Kinnula, Aakash Gautam et al.

This paper examines how children’s capacity to imagine educational futures is shaped by the conditions under which participatory speculative design is introduced. Drawing on workshops with 47 eighth-grade students in India, we explore how scaffolding influences engagement with emerging technologies and future-oriented thinking. Across two sessions, students encountered generative Artificial Intelligence (AI), virtual reality, and a social robot, engaging in design fiction and scenario drawing. Our findings show that rather than generating distant fantasies, speculative design enabled a critical examination of students’ existing educational contexts. With careful scaffolding, children articulated transformative visions that challenged exam-centric schooling and prioritized emotional well-being; without it, imaginaries remained anchored to present constraints. We contribute to Child-Computer Interaction research by framing scaffolding as a decolonial intervention essential for future-making in high-pressure pedagogical environments. Specifically, we propose affective scaffolding and agency-preserving design as frameworks to bridge emotional gaps and ensure human-centric innovation in the Global South.

Learning0 citations2026-06-13arXiv ->

Physics-conforming Latent Twins

Matthias Chung, Yutong Bu, Deepanshu Verma

Surrogate models are central to scientific machine learning, where they enable fast prediction, simulation, inference, and control for complex physical systems. For time-dependent problems, however, accurate interpolation of training trajectories is not sufficient: reliable surrogates should also respect the conservation laws, invariants, admissibility conditions, and dissipative structures that give those trajectories physical meaning. We introduce Physics-conforming Latent Twins, a framework for learning latent surrogate solution operators whose dynamics satisfy selected physical principles by design. The method builds on the Latent Twin formulation by jointly learning an encoder, a decoder, and a latent flow map between arbitrary time-indexed states, while constraining the latent dynamics to preserve or dissipate prescribed structural quantities. We develop a constraint-transfer viewpoint that connects physical structure in the original state space with compatible constraints in latent space, and prove structure-preservation bounds showing how latent enforcement improves control of physical defects after decoding. We also derive algebraic conditions for latent flow maps that preserve linear and quadratic invariants or enforce dissipative inequalities. Numerical experiments on representative ODE and PDE benchmarks demonstrate improved constraint satisfaction, structural fidelity, and qualitative long-time behavior while maintaining accurate surrogate prediction.

Other0 citations2026-04-01Paper ->

Digital Constitutionalism and Regulation of Online Speech in India: Legal and Constitutional Perspective

Deepanshu Verma

Learning0 citations2026-03-24arXiv ->

Boost Like a (Var)Pro: Trust-Region Gradient Boosting via Variable Projection

Abhijit Chowdhary, Elizabeth Newman, Deepanshu Verma

Gradient boosting, a method of building additive ensembles from weak learners, has established itself as a practical and theoretically-motivated approach to approximate functions, especially using decision tree weak learners. Comparable methods for smooth parametric learners, such as neural networks, remain less developed in both training methodology and theory. To this end, we introduce \texttt{VPBoost} ({\bf V}ariable {\bf P}rojection {\bf Boost}ing), a gradient boosting algorithm for separable smooth approximators, i.e., models with a smooth nonlinear featurizer followed by a final linear mapping. \texttt{VPBoost} fuses variable projection, a training paradigm for separable models that enforces optimality of the linear weights, with a second-order weak learning strategy. The combination of second-order boosting, separable models, and variable projection give rise to a closed-form solution for the optimal linear weights and a natural interpretation of \VPBoost as a functional trust-region method. We thereby leverage trust-region theory to prove \VPBoost converges to a stationary point under mild geometric conditions and, under stronger assumptions, achieves a superlinear convergence rate. Comprehensive numerical experiments on synthetic data, image recognition, and scientific machine learning benchmarks demonstrate that \VPBoost learns an ensemble with improved evaluation metrics in comparison to gradient-descent-based boosting and attains competitive performance relative to an industry-standard decision tree boosting algorithm.

Theory0 citations2026-02-25Paper ->

Label-free milk biopsy using nanochannel-based biosensors for early-stage bovine mastitis screening

Deepanshu Verma, Hedieh Haji-Hashemi, Beatriz Prieto-Simón

A label-free electrochemical biosensor is presented for the detection of miRNA-223, a host immune-derived biomarker upregulated in early mastitis. The biosensor consists of porous anodic alumina (pAAO) membranes featuring high-aspect-ratio porous structure, functionalized with ssDNA probes. This nanochannel-based design increases surface area for probe immobilization and enhances sensitivity by amplifying hybridization-induced changes in ionic transport. Upon hybridization with miRNA-223 to the immobilized ssDNA probe, partial pore blockage impedes the diffusion of a redox probe added to the measuring solution. This change in diffusion is quantified via square wave voltammetry. The biosensor enables direct miRNA detection in raw milk, eliminating the need for RNA extraction or amplification. The biosensor was systematically optimized for pore diameter, probe concentration, and blocking conditions, and demonstrated consistent signal suppression in the presence of synthetic miRNA-223 across a dynamic range from 0.1 pM to 1 nM in both phosphate buffer and 0.1% raw milk. Application to milk collected from clinically classified cows showed clear discrimination between healthy and subclinical samples, with an area under the receiver operating characteristic curve of 0.96. Statistical analysis across 30 replicate sensor readings confirmed significant group-level discrimination (p = 0.016, Mann–Whitney U test). The biosensor’s high sensitivity and specificity are attributed to its diffusion-limited pore-based architecture and stable surface functionalization, which together enable selective and reproducible hybridization responses. Its demonstrated compatibility with raw milk furthers its robustness and analytical reliability under real sample conditions. The ability to detect early-stage, immune-derived miRNAs in minimally processed milk (0.1% v/v raw milk in phosphate buffer) supports the deployment of this biosensor in on-farm, real-time surveillance systems. By eliminating reliance on pathogen detection and enabling pre-symptomatic classification, this work aims to contribute to improved livestock health management, antimicrobial stewardship, and broader one-health objectives.

Learning0 citations2026-01-31arXiv ->

On the Convergence of Jacobian-Free Backpropagation for Optimal Control Problems with Implicit Hamiltonians

Eric Gelphman, Deepanshu Verma, N. Yang, Stanley Osher, Samy Wu Fung

Optimal feedback control with implicit Hamiltonians poses a fundamental challenge for learning-based value function methods due to the absence of closed-form optimal control laws. Recent work~\cite{gelphman2025end} introduced an implicit deep learning approach using Jacobian-Free Backpropagation (JFB) to address this setting, but only established sample-wise descent guarantees. In this paper, we establish convergence guarantees for JFB in the stochastic minibatch setting, showing that the resulting updates converge to stationary points of the expected optimal control objective. We further demonstrate scalability on substantially higher-dimensional problems, including multi-agent optimal consumption and swarm-based quadrotor and bicycle control. Together, our results provide both theoretical justification and empirical evidence for using JFB in high-dimensional optimal control with implicit Hamiltonians.

Other0 citations2026-01-01Paper ->

Extracellular Protein Quality Control in Tau Pathology.

Prasun Kumar Bhunia, Deepanshu Verma, Priyanka Vimal, Prasad Kasturi

Learning0 citations2025-11-12arXiv ->

Regularity and error estimates in physics-informed neural networks for the Kuramoto-Sivashinsky equation

Mohammad Mahabubur Rahman, Deepanshu Verma

Due to its nonlinearity, bi-harmonic dissipation, and backward heat-like term in the absence of a divergence-free condition, the $2$-D/$3$-D Kuramoto-Sivashinsky equation poses significant challenges for both mathematical analysis and numerical approximation. These difficulties motivate the development of methods that blend classical analysis with numerical approximation approaches embodied in the framework of the physics-informed neural networks (PINNs). In addition, despite the extensive use of PINN frameworks for various linear and nonlinear PDEs, no study had previously established rigorous error estimates for the Kuramoto-Sivashinsky equation within a PINN setting. In this work, we overcome the inherent challenges, and establish several global regularity criteria based on space-time integrability conditions in Besov spaces. We then derive the first rigorous error estimates for the PINNs approximation of the Kuramoto-Sivashinsky equation and validate our theoretical error bounds through numerical simulations.

MPC/Planning0 citations2025-10-01arXiv ->

Randomized Matrix Sketching for Neural Network Training and Gradient Monitoring

H. Antil, Deepanshu Verma

Neural network training relies on gradient computation through backpropagation, yet memory requirements for storing layer activations present significant scalability challenges. We present the first adaptation of control-theoretic matrix sketching to neural network layer activations, enabling memory-efficient gradient reconstruction in backpropagation. This work builds on recent matrix sketching frameworks for dynamic optimization problems, where similar state trajectory storage challenges motivate sketching techniques. Our approach sketches layer activations using three complementary sketch matrices maintained through exponential moving averages with adaptive rank adjustment, automatically balancing memory efficiency against approximation quality. Empirical evaluation on MNIST, CIFAR-10, and physics-informed neural networks demonstrates a controllable accuracy-memory tradeoff. We demonstrate a gradient monitoring application on MNIST showing how sketched activations enable real-time gradient norm tracking with minimal memory overhead. These results establish that sketched activation storage provides a viable path toward memory-efficient neural network training and analysis.

MPC/Planning0 citations2025-10-01arXiv ->

End-to-End Training of High-Dimensional Optimal Control with Implicit Hamiltonians via Jacobian-Free Backpropagation

Eric Gelphman, Deepanshu Verma, N. Yang, Stanley Osher, Samy Wu Fung

Neural network approaches that parameterize value functions have succeeded in approximating high-dimensional optimal feedback controllers when the Hamiltonian admits explicit formulas. However, many practical problems, such as the space shuttle reentry problem and bicycle dynamics, among others, may involve implicit Hamiltonians that do not admit explicit formulas, limiting the applicability of existing methods. Rather than directly parameterizing controls, which does not leverage the Hamiltonian's underlying structure, we propose an end-to-end implicit deep learning approach that directly parameterizes the value function to learn optimal control laws. Our method enforces physical principles by ensuring trained networks adhere to the control laws by exploiting the fundamental relationship between the optimal control and the value function's gradient; this is a direct consequence of the connection between Pontryagin's Maximum Principle and dynamic programming. Using Jacobian-Free Backpropagation (JFB), we achieve efficient training despite temporal coupling in trajectory optimization. We show that JFB produces descent directions for the optimal control objective and experimentally demonstrate that our approach effectively learns high-dimensional feedback controllers across multiple scenarios involving implicit Hamiltonians, which existing methods cannot address.

Learning0 citations2025-09-24arXiv ->

Latent Twins

Matthias Chung, Deepanshu Verma, M. Collins, A. Subrahmanya, Varuni Katti Sastry et al.

Over the past decade, scientific machine learning has transformed the development of mathematical and computational frameworks for analyzing, modeling, and predicting complex systems. From inverse problems to numerical partial differential equations (PDEs), dynamical systems, and model reduction, these advances have pushed the boundaries of what can be simulated. Yet they have often progressed in parallel, with representation learning and algorithmic solution methods evolving largely as separate pipelines. With Latent Twins, we propose a unifying mathematical framework that creates a hidden surrogate in latent space for the underlying equations. Whereas digital twins mirror physical systems in the digital world, Latent Twins mirror mathematical systems in a learned latent space governed by operators. Through this lens, classical modeling, inversion, model reduction, and operator approximation all emerge as special cases of a single principle. We establish the fundamental approximation properties of Latent Twins for both ordinary differential equations (ODEs) and PDEs and demonstrate the framework across three representative settings: (i) canonical ODEs, capturing diverse dynamical regimes; (ii) a PDE benchmark using the shallow-water equations, contrasting Latent Twin simulations with deep operator network and forecasts with a four-dimensional variational method baseline; and (iii) a challenging real-data geopotential reanalysis dataset, reconstructing and forecasting from sparse, noisy observations. Latent Twins provide a compact, interpretable surrogate for solution operators that evaluate across arbitrary time gaps in a single-shot, while remaining compatible with scientific pipelines such as assimilation, control, and uncertainty quantification. Looking forward, this framework offers scalable, theory-grounded surrogates that bridge data-driven representation learning and classical scientific modeling across disciplines.

MPC/Planning0 citations2025-09-22arXiv ->

Zero-Shot Transferable Solution Method for Parametric Optimal Control Problems

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

This paper presents a transferable solution method for optimal control problems with varying objectives using function encoder (FE) policies. Traditional optimization-based approaches must be re-solved whenever objectives change, resulting in prohibitive computational costs for applications requiring frequent evaluation and adaptation. The proposed method learns a reusable set of neural basis functions that spans the control policy space, enabling efficient zero-shot adaptation to new tasks through either projection from data or direct mapping from problem specifications. The key idea is an offline-online decomposition: basis functions are learned once during offline imitation learning, while online adaptation requires only lightweight coefficient estimation. Numerical experiments across diverse dynamics, dimensions, and cost structures show our method delivers near-optimal performance with minimal overhead when generalizing across tasks, enabling semi-global feedback policies suitable for real-time deployment.

Learning1 citations2025-08-13Paper ->

Efficient Neural Network Approaches for Conditional Optimal Transport with Applications in Bayesian Inference

Z. Wang, R. Baptista, Youssef M. Marzouk, Lars Ruthotto, Deepanshu Verma

Other0 citations2025-08-11Paper ->

Li-Fi: The Future of Wi-Fi

Rajeev Ranjan, Dedakiya Ghanshyam, Aryan Karthik, Deepanshu Verma, Mahesh K. Singh

This research work provides a comprehensive analysis of Light Fidelity (Li-Fi) and Wireless Fidelity (Wi-Fi) technologies. This research also explores their performance metrics, data security and privacy considerations, economic impact, deployment cost, and integration into existing urban infrastructure. The study also considers the recent literature review to evaluate the potential of Li-Fi, a wireless visible light communication technology, as a complement or alternative to dominant Wi-Fi technology. Key findings highlight the Li-Fi’s advantages in data transmission and security due to its use of light to limited areas i.e., the area where the light is illuminated. The paper concludes by discussing the future directions of Li-Fi also exploring its potential role in various applications such as including secure environments and smart cities.

Learning0 citations2025-02-26arXiv ->

Error estimates for viscous Burgers' equation using deep learning method

Wasim Akram, Sagar Gautam, Deepanshu Verma, M. T. Mohan

The article focuses on error estimates as well as stability analysis of deep learning methods for stationary and non-stationary viscous Burgers equation in two and three dimensions. The local well-posedness of homogeneous boundary value problem for non-stationary viscous Burgers equation is established by using semigroup techniques and fixed point arguments. By considering a suitable approximate problem and deriving appropriate energy estimates, we prove the existence of a unique strong solution. Additionally, we extend our analysis to the global well-posedness of the non-homogeneous problem. For both the stationary and non-stationary cases, we derive explicit error estimates in suitable Lebesgue and Sobolev norms by optimizing a loss function in a Deep Neural Network approximation of the solution with fixed complexity. Finally, numerical results on prototype systems are presented to illustrate the derived error estimates.

MPC/Planning0 citations2024-11-25Paper ->

Investigation of Tensile Strength Performance of 3D Printed PLA, ABS and PET-G Materials for Various Industrial Applications

Bijender, Akash Soni, Ankit Boora, Deepanshu Verma

Objective of this paper is to investigate and compare the tensile strength of three commonly used 3D printing materials i.e. Poly Lactic Acid (PLA), Acrylonitrile Butadiene Styrene (ABS), and Polyethylene Terephthalate Glycol (PET-G) for various industrial applications. Tensile strength is a critical mechanical parameter, especially in applications subject to stretching forces. Through experimental testing, the tensile strength of each material was determined. The results revealed distinct mechanical behaviors among the materials, providing valuable insights for material selection and process optimization in additive manufacturing. This research contributes to advancing the understanding of the mechanical performance of 3D printed materials and informs practical applications in various industries.

Other1 citations2024-11-25Paper ->

Time Reduction Analysis Based on Infill Pattern on FDM 3D Printed PLA Material

Ankit Boora, Deepanshu Verma, Bijender, Akash Soni

Fused Deposition Modeling (FDM) used in 3D Printing is a widely used additive manufacturing technology known for its versatility and cost-effectiveness. One critical quality attribute of FDM 3D printing is the infill pattern, which directly affects the mechanical properties, print quality, and production time of printed parts. This paper focuses on analyzing the impact of different infill patterns on time consumption in FDM 3D print time duration. The research methodology involves designing and printing test specimens with varying infill patterns, including but not limited to grid, honeycomb, and gyroid Printing parameters such as layer height, infill density, and print speed are kept constant to isolate the effect of infill patterns on print time. A comprehensive analysis is conducted to measure the print time for each infill pattern and evaluate their influence on the overall printing duration.

Robotics10 citations2024-08-11Paper ->

Emerging Technologies in Global South Classrooms: Teachers Imagining Future of Education

Priyanka Sebastian, Sumita Sharma, N. Iivari, Marianne Kinnula, Charu Monga et al.

Emerging technologies, including artificial intelligence, robots, and virtual reality, are reshaping our world, and driving educational transformations globally, revolutionizing traditional learning. Existing research has pointed out the need to address emerging technologies as part of computational empowerment of children. However, there is little research of computational empowerment of children from teachers’ perspective so far. Based on data from workshop with public school teachers in India, we advocate for an organized integration of smart technologies with an ethical emphasis in the curriculum. Furthermore, we delve into educators' perspectives, exploring their aspirations, needs, challenges, and concerns, offering insights into the future of education.

Learning12 citations2024-03-08Paper ->

Diabetic Retinopathy Eye Disease Detection Using Machine Learning

Ruby Dahiya, Nidhi Agarwal, Sangeeta Singh, Deepanshu Verma, Shivam Gupta

INTRODUCTION: Diabetic retinopathy is the name given to diabetes problems that harm the eyes. Its root cause is damage to the blood capillaries in the tissue that is light-sensitive in the rear of the eye. Over time, having excessive blood sugar may cause to the tiny blood capillaries that nourish the retina to become blocked, severing the retina's blood circulation. As a result, the eye tries to develop new blood arteries. OBJECTIVES: The objective of this research is to analyse and compare various algorithms based on their performance and efficiency in predicting Diabetic Retinopathy. METHODS: To achieve this, an experimental model was developed to predict Diabetic Retinopathy at early stage. RESULTS: The results provide valuable insights into the effectiveness and scalability of these algorithms. The findings of this study contribute to the understanding of various algorithm selection and its impact on the overall performance of models. CONCLUSION: The findings of this study contribute to the understanding of multiple algorithm selection and its impact on the overall performance of models’ accuracy. By applying these algorithms, we can predict disease at early stage such that it can be cured efficiently before it goes worse.

CBF Related Papers
MPC/Planning0 citations2026-07-22arXiv ->

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

Non-CBF Papers
Other72 citations2025-04-01Paper ->

Blockchain Technology in Supply Chain Management: Innovations, Applications, and Challenges

Narendra Kumar, Krishna Kumar, Anurag Aeron, Filippo Verre

Other293 citations2023-08-08Paper ->

An Overview of Plant Phenolics and Their Involvement in Abiotic Stress Tolerance

Krishna Kumar, P. Debnath, S. Singh, Navin Kumar

Secondary metabolites, such as phenols and salicylic, play a crucial role in the regulation of development and tolerance mechanisms against a wide range of stresses. During adverse conditions such as biotic and abiotic stresses, plants induce the biosynthesis of phenolic compounds to provide tolerance. Phenolics are secondary aromatic metabolites synthesized through the shikimate/phenylpropanoid pathway or polyketide acetate/malonate pathway, which produce monomeric and polymeric phenolics. Phenolic compounds in plants not only take part in preventing stresses but also in regulating physiological activities. These compounds significantly regulate both below- and above-ground defense mechanisms. Plants synthesize thousands of phenolic compounds throughout their evolution to survive in changing environments. Environmental factors, such as high light, cold, drought, heavy metals, etc., increase the accumulation of phenolics to neutralize any toxic effects. This review focuses on the biosynthesis of phenolic compounds and their updated studies against abiotic stresses.

Learning0 citations2023-05-09arXiv ->

Graph Neural Network-based surrogate model for granular flows

Yongjin Choi, Krishna Kumar

Accurate simulation of granular flow dynamics is crucial for assessing various geotechnical risks, including landslides and debris flows. Granular flows involve a dynamic rearrangement of particles exhibiting complex transitions from solid-like to fluid-like responses. Traditional continuum and discrete numerical methods are limited by their computational cost in simulating large-scale systems. Statistical or machine learning-based models offer an alternative. Still, they are largely empirical, based on a limited set of parameters. Due to their permutation-dependent learning, traditional machine learning-based models require huge training data to generalize. To resolve these problems, we use a graph neural network, a state-of-the-art machine learning architecture that learns local interactions. Graphs represent the state of dynamically changing granular flows and the interaction laws, such as energy and momentum exchange between grains. We develop a graph neural network-based simulator (GNS) that takes the current state of granular flow and predicts the next state using Euler explicit integration by learning the local interaction laws. We train GNS on different granular trajectories. We then assess the performance of GNS by predicting granular column collapse. GNS accurately predicts flow dynamics for column collapses with different aspect ratios unseen during training. GNS is hundreds of times faster than high-fidelity numerical simulators. The model also generalizes to domains much larger than the training data, handling more than twice the number of particles than it was trained on.

Other0 citations2023-04-04arXiv ->

Geotechnical Parrot Tales (GPT): Harnessing Large Language Models in geotechnical engineering

Krishna Kumar

The widespread adoption of large language models (LLMs), such as OpenAI's ChatGPT, could revolutionize various industries, including geotechnical engineering. However, GPT models can sometimes generate plausible-sounding but false outputs, leading to hallucinations. In this article, we discuss the importance of prompt engineering in mitigating these risks and harnessing the full potential of GPT for geotechnical applications. We explore the challenges and pitfalls associated with LLMs and highlight the role of context in ensuring accurate and valuable responses. Furthermore, we examine the development of context-specific search engines and the potential of LLMs to become a natural interface for complex tasks, such as data analysis and design. We also develop a unified interface using natural language to handle complex geotechnical engineering tasks and data analysis. By integrating GPT into geotechnical engineering workflows, professionals can streamline their work and develop sustainable and resilient infrastructure systems for the future.

Learning27 citations2023-03-31Paper ->

Development of a Reliable Machine Learning Model to Predict Compressive Strength of FRP-Confined Concrete Cylinders

Prashant Kumar, H. Arora, A. Bahrami, Aman Kumar, Krishna Kumar

The degradation of reinforced concrete (RC) structures has raised major concerns in the concrete industry. The demolition of existing structures has shown to be an unsustainable solution and leads to many financial concerns. Alternatively, the strengthening sector has put forward many sustainable solutions, such as the retrofitting and rehabilitation of existing structural elements with fiber-reinforced polymer (FRP) composites. Over the past four decades, FRP retrofits have attracted major attention from the scientific community, thanks to their numerous advantages such as having less weight, being non-corrodible, etc., that help enhance the axial, flexural, and shear capacities of RC members. This study focuses on predicting the compressive strength (CS) of FRP-confined concrete cylinders using analytical models and machine learning (ML) models. To achieve this, a total of 1151 specimens of cylinders have been amassed from comprehensive literature studies. The ML models utilized in the study are Gaussian process regression (GPR), support vector machine (SVM), artificial neural network (ANN), optimized SVM, and optimized GPR models. The input parameters that have been used for prediction include the geometrical characteristics of specimens, the mechanical properties of FRP composite, and the CS of concrete. The results of the five ML models are compared with nineteen analytical models. The results evaluated from the ML algorithms imply that the optimized GPR model has been found to be the best among all other models, demonstrating a higher correlation coefficient, root mean square error, mean absolute percentage error, mean absolute error, a-20 index, and Nash–Sutcliffe efficiency values of 0.9960, 3.88 MPa, 3.11%, 2.17 MPa, 0.9895, and 0.9921, respectively. The R-value of the optimized GPR model is 0.37%, 0.03%, 5.14%, and 2.31% higher than that of the ANN, GPR, SVM, and optimized SVM models, respectively, whereas the root mean square error value of the ANN, GPR, SVM, and optimized SVM models is, respectively, 81.04%, 12.5%, 471.77%, and 281.45% greater than that of the optimized GPR model.

Other51 citations2023-03-21Paper ->

Security issues and challenges in cloud of things-based applications for industrial automation

Neeraj Kumar Pandey, Krishna Kumar, Gaurav Saini, A. Mishra

Due to the COVID-19 outbreak, industries have gained a thrust on contactless processing for computing technologies and industrial automation. Cloud of Things (CoT) is one of the emerging computing technologies for such applications. CoT combines the most emerging cloud computing and the Internet of Things. The development in industrial automation made them highly interdependent because the cloud computing works like a backbone in IoT technology. This supports the data storage, analytics, processing, commercial application development, deployment, and security compliances. Now amalgamation of cloud technologies with IoT is making utilities more useful, smart, service-oriented, and secure application for sustainable development of industrial processes. As the pandemic has increased access to computing utilities remotely, cyber-attacks have been increased exponentially. This paper reviews the CoT’s contribution to industrial automation and the various security features provided by different tools and applications used for the circular economy. The in-depth analysis of security threats, availability of different features corresponding the security issues in traditional and non-traditional CoT platforms used in industrial automation have been analysed. The security issues and challenges faced by IIoT and AIoT in industrial automation have also been addressed.

Learning37 citations2023-02-17Paper ->

Machine learning intelligence to assess the shear capacity of corroded reinforced concrete beams

Aman Kumar, H. Arora, N. R. Kapoor, Krishna Kumar, M. Hadzima-Nyarko et al.

The ability of machine learning (ML) techniques to forecast the shear strength of corroded reinforced concrete beams (CRCBs) is examined in the present study. These ML techniques include artificial neural networks (ANN), adaptive-neuro fuzzy inference systems (ANFIS), decision tree (DT) and extreme gradient boosting (XGBoost). A thorough databank with 140 data points about the shear capacity of CRCBs with various degrees of corrosion was compiled after a review of the literature. The inputs parameters of the implemented models are the width of the beam, the effective depth of the beam, concrete compressive strength (CS), yield strength of reinforcement, percentage of longitudinal reinforcement, percentage of transversal reinforcement (stirrups), yield strength of stirrups, stirrups spacing, shear span-to-depth ratio ( a/d ), corrosion degree of main reinforcement, and corrosion degree of stirrups. The coefficient of determination of the ANN, ANFIS, DT, and XGBoost models are 0.9811, 0.9866, 0.9799, and 0.9998, respectively. The MAPE of the XGBoost model is 99.39%, 99.16%, and 99.28% lower than ANN, ANFIS, and DT models. According to the results of the sensitivity examination, the shear strength of the CRCBs is most affected by the depth of the beam, stirrups spacing, and the a/d . The graphical displays of the Taylor graph, violin plot, and multi-histogram plot additionally support the XGBoost model's dependability and precision. In addition, this model demonstrated good experimental data fit when compared to other analytical and ML models. Accurate prediction of shear strength using the XGBoost approach confirmed that this approach is capable of handling a wide range of data and can be used as a model to predict shear strength with higher accuracy. The effectiveness of the developed XGBoost model is higher than the existing models in terms of precision, economic considerations, and safety, as indicated by the comparative study.

Learning39 citations2022-10-01Paper ->

Environmental occurrence, toxicity and remediation of perchlorate - A review.

Krishna Kumar, S. Kavitha, K. Parameswari, A. Sakunthala, P. Sathishkumar

Perchlorate (ClO4-) comes under the class of contaminants called the emerging contaminants that will impact environment in the near future. A strong oxidizer by nature, perchlorate has received significant observation due to its occurrence, reactive nature, and persistence in varied environments such as surface water, groundwater, soil, and food. Perchlorate finds its use in number of industrial products ranging from missile fuel, fertilizers, and fireworks. Perchlorate exposure occurs when naturally occurring or manmade perchlorate in water or food is ingested. Perchlorate ingestion affects iodide absorption into the thyroid, thereby causing a decrease in the synthesis of thyroid hormone, a very crucial component needed for metabolism, neural development, and a number of other physiological functions in the body. Perchlorate remediation from ground water and drinking water is carried out through a series of physical-chemical techniques like ion (particle) transfer and reverse osmosis. However, the generation of waste through these processes are difficult to manage, so the need for alternative treatment methods occur. This review talks about the hybrid technologies that are currently researched and gaining momentum in the treatment of emerging contaminants, namely perchlorate.

Learning36 citations2022-09-14Paper ->

Prognosis of compressive strength of fly‐ash‐based geopolymer‐modified sustainable concrete with ML algorithms

Aman Kumar, H. Arora, N. R. Kapoor, Krishna Kumar

Sustainable concrete is the demand of the present era to reduce carbon emissions. Fly‐ash‐based geopolymer (FLAG) concrete has been used in the construction industry for more than one and a half decades. The compressive strength (CS) of concrete plays a crucial role in the mechanical properties of concrete. Laboratory experiments take a huge amount of time and cost to estimate the CS of concrete. Although analytical methods exist to estimate the CS of concrete, but these models cannot forecast the CS of concrete with better precision due to the complexity of the design mixes. The machine learning (ML)‐based models have been helpful in estimating the CS of concrete with high accuracy and reliability. In this article, four ML algorithms (support vector machine [SVM], linear regression [LR], ensemble learning [EL], and Gaussian process regression [GPR]) and three optimized ML algorithms (EL, SVM, and GPR) have been used to estimate the CS of FLAG concrete. The R‐value of LR, EL, SVMR, GPR, optimized EL, optimized SVMR and optimized GPR models are 0.8916, 0.9172, 0.9313, 0.9529, 0.9459, 0.9348 and 0.9590, respectively. The accuracy of the optimized GPR model with an R‐value of 0.9590 and RMSE value of 1.7132 MPa outperformed all other ML models. The performances of all the developed models have been illustrated through Taylor diagram and error plot. The feature importance of the input parameters has been explained with the explainable ML technique. The developed, optimized GPR model can be reliable tool to estimate the CS with greater accuracy and also reducing time and cost.

Other34 citations2022-05-13Paper ->

Dimensions of Internet of Things: Technological Taxonomy Architecture Applications and Open Challenges—A Systematic Review

Krishna Kumar, Aman Kumar, Narendra Kumar, M. Mohammed, Alaa S. Al-Waisy et al.

We are traversing the growing emerging technology paradigms in today’s advanced technological world. In this present era, the Internet of Things (IoT) is extensively used in all sectors. IoT is the ecosystem of smart devices which contains sensors, smart objects, networking, and processing units. These integrated devices provide better services to the end user. IoT is impacting our environment and is becoming one of the most popular technologies. The leading use of IoT in human life is to track activities anywhere at any time. The utmost utilities achieved by IoT applications are decision-making and monitoring for efficient and effective management. In this paper, an extensive literature review on IoT has been done using the systematic literature review (SLR) technique. The main focus areas include commercial, environmental, healthcare, industrial, and smart cities. The issues related to the IoT are also discussed in detail. The purpose of this review is to identify the major areas of applications, different popular architectures, and their challenges. The various IoT applications are compared in accordance with technical features such as quality of service and environmental evaluation. This study can be utilized by the researchers to understand the concept of IoT and provides a roadmap to develop strategies for their future research work.

Other65 citations2022-05-01Paper ->

IEHC: An efficient image encryption technique using hybrid chaotic map

Krishna Kumar, Satyabrata Roy, U. Rawat, S. Malhotra

Learning55 citations2022-03-07Paper ->

Machine Learning-Based CO2 Prediction for Office Room: A Pilot Study

N. R. Kapoor, Ashok Kumar V, Anuj Kumar, Aman Kumar, M. Mohammed et al.

Air pollution is increasing profusely in Indian cities as well as throughout the world, and it poses a major threat to climate as well as the health of all living things. Air pollution is the reason behind degraded indoor air quality (IAQ) in urban buildings. Carbon dioxide (CO2) is the main contributor to indoor pollution as humans themselves are one of the generating sources of this pollutant. The testing and monitoring of CO2 consume cost and time and require smart sensors. Thus, to solve these limitations, machine learning (ML) has been used to predict the concentration of CO2 inside an office room. This study is based on the data collected through real-time measurements of indoor CO2, number of occupants, area per person, outdoor temperature, outer wind speed, relative humidity, and air quality index used as input parameters. In this study, ten algorithms, namely, artificial neural network (ANN), support vector machine (SVM), decision tree (DT), Gaussian process regression (GPR), linear regression (LR), ensemble learning (EL), optimized GPR, optimized EL, optimized DT, and optimized SVM, were used to predict the concentration of CO2. It has been found that the optimized GPR model performs better than other selected models in terms of prediction accuracy. The result of this study indicated that the optimized GPR model can predict the concentration of CO2 with the highest prediction accuracy having R , RMSE, MAE, NS, and a20-index values of 0.98874, 4.20068 ppm, 3.35098 ppm, 0.9817, and 1, respectively. This study can be utilized by the designers, researchers, healthcare professionals, and smart city developers to analyse the indoor air quality for designing air ventilation systems and monitoring CO2 level inside the buildings.

Learning133 citations2022-02-19Paper ->

Compressive Strength Prediction of Lightweight Concrete: Machine Learning Models

Aman Kumar, H. Arora, N. R. Kapoor, M. Mohammed, Krishna Kumar et al.

Concrete is the most commonly used construction material. The physical properties of concrete vary with the type of concrete, such as high and ultra-high-strength concrete, fibre-reinforced concrete, polymer-modified concrete, and lightweight concrete. The precise prediction of the properties of concrete is a problem due to the design code, which typically requires specific characteristics. The emergence of a new category of technology has motivated researchers to develop mechanical strength prediction models using Artificial Intelligence (AI). Empirical and statistical models have been extensively used. These models require a huge amount of laboratory data and still provide inaccurate results. Sometimes, these models cannot predict the properties of concrete due to complexity in the concrete mix design and curing conditions. To conquer such issues, AI models have been introduced as another approach for predicting the compressive strength and other properties of concrete. This article discusses machine learning algorithms, such as Gaussian Progress Regression (GPR), Support Vector Machine Regression (SVMR), Ensemble Learning (EL), and optimized GPR, SVMR, and EL, to predict the compressive strength of Lightweight Concrete (LWC). The simulation approaches of these trained models indicate that AI can provide accurate prediction models without undertaking extensive laboratory trials. Each model’s applicability and performance were rigorously reviewed and assessed. The findings revealed that the optimized GPR model (R = 0.9803) used in this study had the greatest accuracy. In addition, the optimized SVMR and GPR model showed good performance, with R-values 0.9777 and 0.9740, respectively. The proposed model is economic and efficient, and can be adopted by researchers and engineers to predict the compressive strength of LWC.

Learning39 citations2022-01-12Paper ->

Prediction of FRCM–Concrete Bond Strength with Machine Learning Approach

Aman Kumar, H. Arora, Krishna Kumar, M. Mohammed, A. Majumdar et al.

Fibre-reinforced cement mortar (FRCM) has been widely utilised for the repair and restoration of building structures. The bond strength between FRCM and concrete typically takes precedence over the mechanical parameters. However, the bond behaviour of the FRCM–concrete interface is complex. Due to several failure modes, the prediction of bond strength is difficult to forecast. In this paper, effective machine learning models were employed in order to accurately predict the FRCM–concrete bond strength. This article employed a database of 382 test results available in the literature on single-lap and double-lap shear experiments on FRCM–concrete interfacial bonding. The compressive strength of concrete, width of concrete block, FRCM elastic modulus, thickness of textile layer, textile width, textile bond length, and bond strength of FRCM–concrete interface have been taken into consideration with popular machine learning models. The paper estimates the predictive accuracy of different machine learning models for estimating the FRCM–concrete bond strength and found that the GPR model has the highest accuracy with an R-value of 0.9336 for interfacial bond strength prediction. This study can be utilising in the estimation of bond strength to minimise the experimentation cost in minimum time.

Learning98 citations2021-12-01Paper ->

Robust and sparsity-aware adaptive filters: A Review

Krishna Kumar, Rajlaxmi Pandey, M. Karthik, Sankha Subhra Bhattacharjee, Nithin V. George

Other34 citations2021-04-13Paper ->

Sex differences in prevalence and risk factors of hypertension in India: Evidence from the National Family Health Survey-4

Krishna Kumar, Sheuli Misra

To estimate sex-specific prevalence and associated socio-economic, demographic, and lifestyle risk factors of hypertension in India. We used data from the National Family Health Survey (NFHS-4) of 2015–16. The analysis based on 6,99,686 women (15–49 years) and 1,12,122 men (15–54 years) whose blood pressure (BP) were measured during the survey. Bivariate distribution was used to show the prevalence of hypertension and, maps were used to present its spatial patterns. Logistic regression model was used to identify sex-specific association between risk factors and hypertension. Results show that the overall prevalence of hypertension was 16.32% among men and 11.56% among women. We also found that the prevalence of hypertension across selected socio-economic, demographic and lifestyle background characteristics and in a majority of the states was higher among men compared to women. Odds ratios from logistic regression analysis direct sex-related differences in risk factors. Hypertension increases with an increase in age and the risk is higher among older women (AOR, 5.58; 95% CI, 5.16–6.03 for women aged 40–49 and AOR, 4.24; 95% CI, 3.94–4.57 for men aged 50–54) compared to men. Education, types of jobs (specially technical, administrative and managerial), marital status and non-vegetarian diet were significantly associated with hypertension in men. While other than age; non-working, consumption of alcohol, and being a diabetic was found to be major risk factors for this disease among women. There are sex-related differences in prevalence as well as risk factors of hypertension in India. In order to prevent early developments of hypertension, awareness related to changing lifestyles such as a diet rich in fruits, vegetables as well as screening to control BP should be promoted among youths and adults in India. The study also recommends sex-specific approaches in health infrastructure and policies besides increasing public awareness.

Learning45 citations2021-01-01Paper ->

Joint Logarithmic Hyperbolic Cosine Robust Sparse Adaptive Algorithms

Krishna Kumar, Sankha Subhra Bhattacharjee, Nithin V. George

Recently, the logarithmic hyperbolic cosine adaptive filter (LHCAF) was proposed and was seen to demonstrate excellent robustness against impulsive interference. However, for the modelling of sparse systems, it may not provide optimal performance as it does not take into account the sparse nature of the system. To improve the modelling accuracy and convergence performance, a sparsity aware zero attraction LHCAF (ZA-LHCAF) and a reweighted zero attraction LHCAF (RZA-LHCAF) is proposed. To further improve the performance for modelling of sparse systems in impulsive environments, a joint logarithmic hyperbolic cosine function (JLHCF) is proposed as the cost function. The corresponding update rule, called the joint logarithmic hyperbolic cosine adaptive filter (JLHCAF) is deduced and the bound on learning rate is derived. A room equalization scenario is also considered and an improved sparsity aware robust algorithm based on JLHCF, namely the filtered-x JLHCAF (Fx-JLHCAF) is proposed for the same. Extensive simulation studies carried out for different system identification scenarios, under Gaussian and non-Gaussian disturbances and a room equalization scenario, demonstrate the superior performance achieved by JLHCAF over existing sparsity aware robust adaptive filters.

Learning75 citations2021Paper ->

Exponential Hyperbolic Cosine Robust Adaptive Filters for Audio Signal Processing

Krishna Kumar, Rajlaxmi Pandey, Sankha Subhra Bhattacharjee, Nithin V. George

In recent years, correntropy-based algorithms which include maximum correntropy criterion (MCC), generalized MCC (GMCC), kernel MCC (KMCC) and hyperbolic cosine function-based algorithms such as hyperbolic cosine adaptive filter (HCAF), logarithmic HCAF (LHCAF), least lncosh (Llncosh) have been widely utilized in adaptive filtering due to their robustness towards non-Gaussian/impulsive background noises. However, the performance of such algorithms suffers from high steady-state misalignment. To minimize the steady-state misalignment along with having comparable computational complexity, an exponential hyperbolic cosine function (EHCF) based new robust norm is introduced and a corresponding EHCF based adaptive filter called exponential hyperbolic cosine adaptive filter (EHCAF) is developed in this letter. Further, computational complexity and bound on learning rate for stability of the proposed algorithm is also studied. A set of simulation studies has been carried out for system identification scenario to assess the performance of the proposed algorithm. Further, EHCAF algorithm has been extended and the filtered-x EHCAF (Fx-EHCAF) algorithm is proposed for robust room equalization.

Learning29 citations2021Paper ->

An Optimized Neuro-Bee Algorithm Approach to Predict the FRP-Concrete Bond Strength of RC Beams

Aman Kumar, H. Arora, M. Mohammed, Krishna Kumar, J. Nedoma

Over the world, there is growing worry about the corrosion of reinforced concrete structures. Structure repair, rehabilitation, replacement, and new structures all require cost-effective and long-lasting technologies. Fiber Reinforced Polymer (FRP) has been widely employed in both retrofitting existing structures and building new ones. Due to its varied qualities in reinforced concrete and masonry constructions as a repair composite material, FRP have seen a rise in use over the last decade. This material have several advantages such as high stiffness-to-weight and strength-to-weight ratios, light weight, possibly high longevity, and relative ease of usage in the field. Among all the parameters the bond between concrete and FRP composite play an important role in the strengthening of structures. However, the bond behaviour of the FRP-concrete interface is complex, with several failure modes, making the bond strength difficult to forecast, resulting in the FRP strengthened concrete structure. To overcome such kind of issues machine learning models are sufficient to forecast the bond strength of FRP-concrete. In this article Artificial Neural Network (ANN), optimized Artificial Bee Colony (ABC)-ANN and Gaussian Process Regression (GPR) algorithms are deployed to predict the bond strength. The R-value of ABC-ANN and GPR models are 0.9514 and 0.9618 respectively. This research aids researchers in estimating bond strength in less time, at a lower cost, and with less experimental work.

MPC/Planning82 citations2020-09-05Paper ->

Enhanced Prediction of Intra-day Stock Market Using Metaheuristic Optimization on RNN–LSTM Network

Krishna Kumar, M. T. U. Haider

CBF Related Papers
MPC/Planning0 citations2026-07-22arXiv ->

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

CBF Related Papers
MPC/Planning0 citations2026-07-22arXiv ->

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

MPC/Planning0 citations2026-07-22arXiv ->

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

Theory0 citations2026-03-19arXiv ->

Mean-Field Control Barrier Functions for Stochastic Multi-Agent Systems

Cinzia Tomaselli, Gian Carlo Maffettone, Samy Wu Fung, L. Nurbekyan, M. di Bernardo

Many applications involving multi-agent systems require fulfilling safety constraints. Control barrier functions offer a systematic framework to enforce forward invariance of safety sets. Recent work extended this paradigm to mean-field scenarios, where the number of agents is large enough to make density-space descriptions a reasonable workaround for the curse of dimensionality. However, an open gap in the recent literature concerns the development of mean-field control barrier functions for Fokker-Planck (advection-diffusion) equations. In this work, we address this gap, enabling safe mean-field control of agents with stochastic microscopic dynamics. We provide bounded stability guarantees under safety corrections and corroborate our results through numerical simulations in two representative scenarios, coverage and shepherding control of multi-agent systems.

Robotics0 citations2024-09-27arXiv ->

Mean-Field Control Barrier Functions: A Framework for Real-Time Swarm Control

Samy Wu Fung, L. Nurbekyan

Control Barrier Functions (CBFs) are an effective methodology to ensure safety and performative efficacy in real-time control applications such as power systems, resource allocation, autonomous vehicles, robotics, etc. This approach ensures safety independently of the high-level tasks that may have been pre-planned off-line. For example, CBFs can be used to guarantee that a vehicle will remain in its lane. However, when the number of agents is large, computation of CBFs can suffer from the curse of dimensionality in the multi-agent setting. In this work, we present Mean-field Control Barrier Functions (MF-CBFs), which extends the CBF framework to the mean-field (or swarm control) setting. The core idea is to model a population of agents as probability measures in the state space and build corresponding control barrier functions. Similar to traditional CBFs, we derive safety constraints on the (distributed) controls but now relying on the differential calculus in the space of probability measures.

Non-CBF Papers
MPC/Planning0 citations2026-05-11arXiv ->

Implicit Neural Optimal Transport via Fixed-Point Optimization

Yesom Park, Eric Gelphman, Stanley Osher, Samy Wu Fung

We propose an implicit neural formulation of optimal transport that eliminates adversarial min--max optimization and multi-network architectures commonly used in existing approaches. Our key idea is to parameterize a single potential in the Kantorovich dual and reformulate the associated c-transform as a proximal fixed-point problem. This yields a stable single-network framework in which dual feasibility is enforced exactly through proximal optimality conditions rather than adversarial training. Despite the inner fixed-point computation, gradients can be computed without differentiating through the fixed-point iterations, enabling efficient training without requiring implicit differentiation. We further establish convergence of stochastic gradient descent. The resulting framework is efficient, scalable, and broadly applicable: it simultaneously recovers forward and backward transport maps and naturally extends to class-conditional settings. Experiments on high-dimensional Gaussian benchmarks, physical datasets, and image translation tasks demonstrate strong transport accuracy together with improved training stability and favorable computational and memory efficiency.

MPC/Planning0 citations2026-03-13arXiv ->

Probabilistic Gaussian Homotopy: A Probability-Space Continuation Framework for Nonconvex Optimization

Eshed Gal, Samy Wu Fung, Eldad Haber

We introduce Probabilistic Gaussian Homotopy (PGH), a probability-space continuation framework for nonconvex optimization. Unlike classical Gaussian homotopy, which smooths the objective and uniformly averages gradients, PGH deforms the associated Boltzmann distribution and induces Boltzmann-weighted aggregation of perturbed gradients, which exponentially biases descent directions toward low-energy regions. We show that PGH corresponds to a log-sum-exp (soft-min) homotopy that smooths a nonconvex objective at scale $\lambda>0$ and recovers the original objective as $\lambda\to 0$, yielding a posterior-mean generalization of the Moreau envelope, and we derive a dynamical system governing minimizer evolution along an annealed homotopy path. This establishes a principled connection between Gaussian continuation, Bayesian denoising, and diffusion-style smoothing. We further propose Probabilistic Gaussian Homotopy Optimization (PGHO), a practical stochastic algorithm based on Monte Carlo gradient estimation, and demonstrate strong performance on high-dimensional nonconvex benchmarks and sparse recovery problems where classical gradient methods and objective-space smoothing frequently fail.

MPC/Planning0 citations2026-03-06arXiv ->

A Gauss-Newton Method with No Additional PDE Solves Beyond Gradient Evaluation for Large-Scale PDE-Constrained Inverse Problems

Cash Cherry, Samy Wu Fung, L. Tenorio, Ebru Bozdag

Partial Differential Equation (PDE)-constrained optimization problems often take the form of an optimization of an objective function given as a sum of loss terms. Each function or gradient evaluation requires one or more PDE solves, which render these problems computationally demanding. While Gauss-Newton methods are well-suited for large-scale PDE-constrained optimization, their application to settings such as Full-Waveform Inversion (FWI) is hindered by the need for additional PDE solves to compute Jacobian-vector products. This paper proposes a Gauss-Newton approach that eliminates the need for extra PDE solves beyond those required for gradient computation. Our numerical experiments on FWI demonstrate that the proposed method achieves the efficiency of gradient-based schemes while retaining the fast convergence of Gauss-Newton methods.

Learning0 citations2026-01-31arXiv ->

On the Convergence of Jacobian-Free Backpropagation for Optimal Control Problems with Implicit Hamiltonians

Eric Gelphman, Deepanshu Verma, N. Yang, Stanley Osher, Samy Wu Fung

Optimal feedback control with implicit Hamiltonians poses a fundamental challenge for learning-based value function methods due to the absence of closed-form optimal control laws. Recent work~\cite{gelphman2025end} introduced an implicit deep learning approach using Jacobian-Free Backpropagation (JFB) to address this setting, but only established sample-wise descent guarantees. In this paper, we establish convergence guarantees for JFB in the stochastic minibatch setting, showing that the resulting updates converge to stationary points of the expected optimal control objective. We further demonstrate scalability on substantially higher-dimensional problems, including multi-agent optimal consumption and swarm-based quadrotor and bicycle control. Together, our results provide both theoretical justification and empirical evidence for using JFB in high-dimensional optimal control with implicit Hamiltonians.

MPC/Planning0 citations2026-01-29arXiv ->

Operator Splitting with Hamilton-Jacobi-based Proximals

N. Di, Eric C. Chi, Samy Wu Fung

Operator splitting algorithms are a cornerstone of modern first-order optimization, decomposing complex problems into simpler subproblems solved via proximal operators. However, most functions lack closed-form proximal operators, which has long restricted these methods to a narrow set of problems. Hamilton-Jacobi-based proximal operator (HJ-Prox) is a recent derivative-free Monte Carlo technique based on Hamilton-Jacobi PDE theory, that approximates proximal operators numerically. In this work, we introduce a unified framework for operator splitting via HJ-Prox, which allows for deployment of operator splitting even when functions are not proximable. We prove that replacing exact proximal steps with HJ-Prox in algorithms such as proximal point, proximal gradient descent, Douglas-Rachford splitting, Davis-Yin splitting, and primal-dual hybrid gradient preserves convergence guarantees under mild assumptions. Numerical experiments demonstrate HJ-Prox is competitive and effective on a wide variety of statistical learning tasks.

MPC/Planning0 citations2026-01-20Paper ->

Correction: A Primal-Dual Price-Optimization Method for Computing Equilibrium Prices in Mean-Field Games Models

Xu Wang, Samy Wu Fung, L. Nurbekyan

Learning0 citations2026Paper ->

Fixed-Point Neural Optimal Transport without Implicit Differentiation

Yesom Park, Eric Gelphman, Stanley Osher, Samy Wu Fung

Other1 citations2025-10-21Paper ->

maze-dataset: Maze Generation with Algorithmic Variety and Representational Flexibility

M. I. Ivanitskiy, Aaron Sandoval, Alex F Spies, Tilman Räuker, Brandon Knutson et al.

MPC/Planning0 citations2025-10-01arXiv ->

End-to-End Training of High-Dimensional Optimal Control with Implicit Hamiltonians via Jacobian-Free Backpropagation

Eric Gelphman, Deepanshu Verma, N. Yang, Stanley Osher, Samy Wu Fung

Neural network approaches that parameterize value functions have succeeded in approximating high-dimensional optimal feedback controllers when the Hamiltonian admits explicit formulas. However, many practical problems, such as the space shuttle reentry problem and bicycle dynamics, among others, may involve implicit Hamiltonians that do not admit explicit formulas, limiting the applicability of existing methods. Rather than directly parameterizing controls, which does not leverage the Hamiltonian's underlying structure, we propose an end-to-end implicit deep learning approach that directly parameterizes the value function to learn optimal control laws. Our method enforces physical principles by ensuring trained networks adhere to the control laws by exploiting the fundamental relationship between the optimal control and the value function's gradient; this is a direct consequence of the connection between Pontryagin's Maximum Principle and dynamic programming. Using Jacobian-Free Backpropagation (JFB), we achieve efficient training despite temporal coupling in trajectory optimization. We show that JFB produces descent directions for the optimal control objective and experimentally demonstrate that our approach effectively learns high-dimensional feedback controllers across multiple scenarios involving implicit Hamiltonians, which existing methods cannot address.

MPC/Planning0 citations2025-09-09arXiv ->

A Monte Carlo Approach for Nonsmooth Convex Optimization via Proximal Splitting Algorithms

N. Di, Eric C. Chi, Samy Wu Fung

Operator splitting algorithms are a cornerstone of modern first-order optimization, relying critically on proximal operators as their fundamental building blocks. However, explicit formulas for proximal operators are available only for limited classes of functions, restricting the applicability of these methods. Recent work introduced HJ-Prox, a zeroth-order Monte Carlo approximation of the proximal operator derived from Hamilton-Jacobi PDEs, which circumvents the need for closed-form solutions. In this work, we extend the scope of HJ-Prox by establishing that it can be seamlessly incorporated into operator splitting schemes while preserving convergence guarantees. In particular, we show that replacing exact proximal steps with HJ-Prox approximations in algorithms such as proximal gradient descent, Douglas-Rachford splitting, Davis-Yin splitting, and the primal-dual hybrid gradient method still ensures convergence under mild conditions.

MPC/Planning0 citations2025-06-04arXiv ->

A primal-dual price-optimization method for computing equilibrium prices in mean-field games models

Xu Wang, Samy Wu Fung, L. Nurbekyan

We develop a simple yet efficient Lagrangian method for computing equilibrium prices in a mean-field game price-formation model. We prove that equilibrium prices are optimal in terms of a suitable criterion and derive a primal-dual gradient-based algorithm for computing them. One of the highlights of our computational framework is the efficient, simple, and flexible implementation of the algorithm using modern automatic differentiation techniques. Our implementation is modular and admits a seamless extension to high-dimensional settings with more complex dynamics, costs, and equilibrium conditions. Additionally, automatic differentiation enables a versatile algorithm that requires only coding the cost functions of agents. It automatically handles the gradients of the costs, thereby eliminating the need to manually form the adjoint equations.

MPC/Planning0 citations2025-05-31arXiv ->

Thinking Out of the Box: Hybrid SAT Solving by Unconstrained Continuous Optimization

Zhiwei Zhang, Samy Wu Fung, Anastasios Kyrillidis, Stanley Osher, M. Vardi

The Boolean satisfiability (SAT) problem lies at the core of many applications in combinatorial optimization, software verification, cryptography, and machine learning. While state-of-the-art solvers have demonstrated high efficiency in handling conjunctive normal form (CNF) formulas, numerous applications require non-CNF (hybrid) constraints, such as XOR, cardinality, and Not-All-Equal constraints. Recent work leverages polynomial representations to represent such hybrid constraints, but it relies on box constraints that can limit the use of powerful unconstrained optimizers. In this paper, we propose unconstrained continuous optimization formulations for hybrid SAT solving by penalty terms. We provide theoretical insights into when these penalty terms are necessary and demonstrate empirically that unconstrained optimizers (e.g., Adam) can enhance SAT solving on hybrid benchmarks. Our results highlight the potential of combining continuous optimization and machine-learning-based methods for effective hybrid SAT solving.

Other0 citations2025-02-28arXiv ->

Recent Advances in Numerical Solutions for Hamilton-Jacobi PDEs

Tingwei Meng, Siting Liu, Samy Wu Fung, Stanley Osher

Hamilton-Jacobi partial differential equations (HJ PDEs) play a central role in many applications such as economics, physics, and engineering. These equations describe the evolution of a value function which encodes valuable information about the system, such as action, cost, or level sets of a dynamic process. Their importance lies in their ability to model diverse phenomena, ranging from the propagation of fronts in computational physics to optimal decision-making in control systems. This paper provides a review of some recent advances in numerical methods to address challenges such as high-dimensionality, nonlinearity, and computational efficiency. By examining these developments, this paper sheds light on important techniques and emerging directions in the numerical solution of HJ PDEs.

Learning0 citations2024-10-09arXiv ->

A Generalization Bound for a Family of Implicit Networks

Samy Wu Fung, Benjamin Berkels

Implicit networks are a class of neural networks whose outputs are defined by the fixed point of a parameterized operator. They have enjoyed success in many applications including natural language processing, image processing, and numerous other applications. While they have found abundant empirical success, theoretical work on its generalization is still under-explored. In this work, we consider a large family of implicit networks defined parameterized contractive fixed point operators. We show a generalization bound for this class based on a covering number argument for the Rademacher complexity of these architectures.

Learning0 citations2024-10-03arXiv ->

On Logical Extrapolation for Mazes with Recurrent and Implicit Networks

Brandon Knutson, Amandin Chyba Rabeendran, M. I. Ivanitskiy, Jordan Pettyjohn, Cecilia G. Diniz Behn et al.

Recent work suggests that certain neural network architectures — particularly recurrent neural networks (RNNs) and implicit neural networks (INNs) — are capable of logical extrapolation. When trained on easy instances of a task, these networks (henceforth: logical extrapolators) can generalize to more difficult instances. Previous research has hypothesized that logical extrapolators do so by learning a scalable, iterative algorithm for the given task which converges to the solution. We examine this idea more closely in the context of a single task: maze solving. By varying test data along multiple axes — not just maze size — we show that models introduced in prior work fail in a variety of ways, some expected and others less so. It remains uncertain whether any of these models has truly learned an algorithm. However, we provide evidence that a certain RNN has approximately learned a form of `deadend-filling'. We show that training these models on more diverse data addresses some failure modes but, paradoxically, does not improve logical extrapolation. We also analyze convergence behavior, and show that models explicitly trained to converge to a fixed point are likely to do so when extrapolating, while models that are not may exhibit more exotic limiting behavior such as limit cycles, even when they correctly solve the problem. Our results (i) show that logical extrapolation is not immune to the problem of goal misgeneralization, and (ii) suggest that analyzing the dynamics of extrapolation may yield insights into designing better logical extrapolators.

Learning0 citations2024-08-09arXiv ->

A hybrid SIAC—data-driven post-processing filter for discontinuities in solutions to numerical PDEs

Soraya Terrab, Samy Wu Fung, Jennifer K. Ryan

We present a post-processing hybrid filter that is only applied to the approximation at the final time and allows for reducing errors away from a shock as well as near a shock for approximation with reduced stabilization applied during time-evolution. This filter is designed for discontinuous Galerkin approximations to PDEs and combines a rigorous moment-based Smoothness-Increasing Accuracy-Conserving (SIAC) filter with a consistent data-driven Convolutional-Neural-Network (CNN) filter. While SIAC improves accuracy in smooth regions, it fails to reduce the O(1)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathcal {O}(1)$$\end{document} errors near discontinuities, particularly in inviscid compressible flows with shocks. Our hybrid SIAC–CNN filter, trained exclusively on top-hat functions, enforces consistency constraints globally and higher-order moment conditions in smooth regions, reducing both ℓ2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _2$$\end{document} and ℓ∞\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _\infty $$\end{document} errors near discontinuities and preserving theoretical accuracy in smooth regions. We demonstrate the effectiveness of the hybrid filter on the Euler equations for the Lax, Sod, and Shu–Osher shock-tube problems.

Other0 citations2024-08-07arXiv ->

Fast Partial Fourier Transforms for Large-Scale Ptychography

Ricardo Parada, Samy Wu Fung, Stanley Osher

Ptychography is a popular imaging technique that combines diffractive imaging with scanning microscopy. The technique consists of a coherent beam that is scanned across an object in a series of overlapping positions, leading to reliable and improved reconstructions. Ptychographic microscopes allow for large fields to be imaged at high resolution at additional computational expense. In this work, we explore the use of the fast Partial Fourier Transforms (PFTs), which efficiently compute Fourier coefficients corresponding to low frequencies. The core idea is to use the PFT in a plug-and-play manner to warm-start existing ptychography algorithms such as the ptychographic iterative engine (PIE). This approach reduces the computational budget required to solve the ptychography problem. Our numerical results show that our scheme accelerates the convergence of traditional solvers without sacrificing quality of reconstruction.

Learning13 citations2024-07-11Paper ->

Three-Operator Splitting for Learning to Predict Equilibria in Convex Games

Daniel McKenzie, Howard Heaton, Qiuwei Li, Samy Wu Fung, Stanley Osher et al.

MPC/Planning0 citations2024-06-04arXiv ->

Laplace Meets Moreau: Smooth Approximation to Infimal Convolutions Using Laplace's Method

R. Tibshirani, Samy Wu Fung, Howard Heaton, Stanley Osher

We study approximations to the Moreau envelope -- and infimal convolutions more broadly -- based on Laplace's method, a classical tool in analysis which ties certain integrals to suprema of their integrands. We believe the connection between Laplace's method and infimal convolutions is generally deserving of more attention in the study of optimization and partial differential equations, since it bears numerous potentially important applications, from proximal-type algorithms to solving Halmiton-Jacobi equations.

MPC/Planning0 citations2024-05-17arXiv ->

Kernel Expansions for High-Dimensional Mean-Field Control with Non-local Interactions

Alexander Vidal, Samy Wu Fung, Stanley Osher, Luis Tenorio, L. Nurbekyan

Mean-field control (MFC) problems aim to find the optimal policy to control massive populations of interacting agents. These problems are crucial in areas such as economics, physics, and biology. We consider the nonlocal setting, where the interactions between agents are governed by a suitable kernel. For N agents, the interaction cost has $\mathcal{O}\left( {{N^2}} \right)$ complexity, which can be prohibitively slow to evaluate and differentiate when N is large. To this end, we propose an efficient primal-dual algorithm that utilizes basis expansions of the kernels. The basis expansions reduce the cost of computing the interactions, while the primal-dual methodology decouples the agents at the expense of solving for a moderate number of dual variables. We also demonstrate that our approach can further be structured in a multi-resolution manner, where we estimate optimal dual variables using a moderate N and solve decoupled trajectory optimization problems for large N. We illustrate the effectiveness of our method on an optimal control of 5000 interacting quadrotors.

CBF Related Papers
Robotics0 citations2026-07-22arXiv ->

Safe and Scalable Multi-Drone Payload Transport via CBF-based Reinforcement Learning with Zero-Shot Sim-to-Real Transfer

Jaeyoun Choi, Oswin So, Songyuan Zhang, Cooper Taylor, Chuchu Fan

Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster response. However, the complex coupled dynamics among drones, cables, and payloads pose significant challenges, and existing approaches remain limited in safety and scalability, particularly in dynamic and unstructured environments. In this work, we propose a learning-based framework for safe and scalable multi-drone cooperative payload transport. We introduce a minimal 2D abstraction that preserves the task-relevant drone-payload coupling required for coordination and safety, while remaining computationally efficient for large-scale learning. Using domain randomization over team size and physical parameters, we train a fully distributed policy via Discrete Graph Control Barrier Function Proximal Policy Optimization (DGPPO), enabling robust zero-shot sim-to-real transfer without fine-tuning. Extensive real-world evaluations demonstrate that a single learned policy generalizes across varying team sizes and task scenarios. Furthermore, multi-group hardware experiments show that the same policy can safely operate in dynamic environments, where other drone teams act as moving obstacles. These results indicate that the proposed framework enables efficient, safe, and scalable multi-drone payload transportation with strong generalization to complex real-world conditions.

Robotics0 citations2026-07-22arXiv ->

Safe and Scalable Multi-Drone Payload Transport Via CBF-Based Reinforcement Learning With Zero-Shot Sim-to-Real Transfer

Jaeyoun Choi, Oswin So, Songyuan Zhang, Cooper Taylor, Chuchu Fan

Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster response. However, the complex coupled dynamics among drones, cables, and payloads pose significant challenges, and existing approaches remain limited in safety and scalability, particularly in dynamic and unstructured environments. In this work, we propose a learning-based framework for safe and scalable multi-drone cooperative payload transport. We introduce a minimal 2D abstraction that preserves the task-relevant drone-payload coupling required for coordination and safety, while remaining computationally efficient for large-scale learning. Using domain randomization over team size and physical parameters, we train a fully distributed policy via Discrete Graph Control Barrier Function Proximal Policy Optimization (DGPPO), enabling robust zero-shot sim-to-real transfer without fine-tuning. Extensive real-world evaluations demonstrate that a single learned policy generalizes across varying team sizes and task scenarios. Furthermore, multi-group hardware experiments show that the same policy can safely operate in dynamic environments, where other drone teams act as moving obstacles. These results indicate that the proposed framework enables efficient, safe, and scalable multi-drone payload transportation with strong generalization to complex real-world conditions.

Non-CBF Papers
Other1 citations2026-02-16Paper ->

Impact of Age on Efficacy and Safety of Advanced Therapies During Induction in Ulcerative Colitis: An Individual Patient Data Pooled Analysis from Randomized Controlled Trials.

Dhruv Ahuja, Jaeyoun Choi, G. Zou, S. Goodwin, V. Jairath et al.

MPC/Planning0 citations2026-01-22arXiv ->

Maximizing Reach-Avoid Probabilities for Linear Stochastic Systems via Control Architectures

Niklas Schmid, Jaeyoun Choi, Oswin So, Chuchu Fan

The maximization of reach-avoid probabilities for stochastic systems is a central topic in the control literature. Yet, the available methods are either restricted to low-dimensional systems or suffer from conservative approximations. To address these limitations, we propose control architectures that combine the flexibility of Markov Decision Processes with the scalability of Model Predictive Controllers. The Model Predictive Controller tracks reference signals while remaining agnostic to the stochasticity and reach-avoid objective. Instead, the reach-avoid probability is maximized by optimally updating the controller's reference online. To achieve this, the closed-loop system, consisting of the system and Model Predictive Controller, is abstracted as a Markov Decision Process in which a new reference can be chosen at every time-step. A feedback policy generating optimal references is then computed via Dynamic Programming. If the state space of the system is continuous, the Dynamic Programming algorithm must be executed on a finite system approximation. Modifications to the Model Predictive Controller enable a computationally efficient robustification of the Dynamic Programming algorithm to approximation errors, preserving bounds on the achieved reach-avoid probability. The approach is validated on a perturbed 12D quadcopter model in cluttered reach-avoid environments proving its flexibility and scalability.

Robotics0 citations2026-01-06arXiv ->

Parameter-Robust MPPI for Safe Online Learning of Unknown Parameters

M. Vahs, Jaeyoun Choi, Niklas Schmid, Jana Tumova, Chuchu Fan

Robots deployed in dynamic environments must remain safe even when key physical parameters are uncertain or change over time. We propose Parameter-Robust Model Predictive Path Integral (PRMPPI) control, a framework that integrates online parameter learning with probabilistic safety constraints. PRMPPI maintains a particle-based belief over parameters via Stein Variational Gradient Descent, evaluates safety constraints using Conformal Prediction, and optimizes both a nominal performance-driven and a safety-focused backup trajectory in parallel. This yields a controller that is cautious at first, improves performance as parameters are learned, and ensures safety throughout. Simulation and hardware experiments demonstrate higher success rates, lower tracking error, and more accurate parameter estimates than baselines.

Learning18 citations2025-08-01Paper ->

Artificial intelligence-based digital pathology using H&E-stained whole slide images in immuno-oncology: from immune biomarker detection to immunotherapy response prediction

Jessica Zhang, Horyun Choi, Yeseul Kim, Jonghanne Park, Sukjoo Cho et al.

Immuno-oncology and the advent of immunotherapies, in particular immune checkpoint inhibitors (ICIs), have fundamentally altered the way we treat cancer. Yet only a small subset of patients actually responds to ICIs, and many face significant adverse effects, making the accurate selection of patients for ICIs essential to the work of immuno-oncology. Immune biomarkers, such as programmed death-ligand 1, microsatellite instability/defective mismatch repair, and tumor mutational burden have been developed for patient selection and stratification for ICIs, though their predictive abilities remain limited. This is due to several challenges: lack of adequate tissue sampling, the time-consuming and subjective nature of manual visual-based quantification techniques, and the growing recognition of the complexity of the tumor microenvironment, for which these tests cannot fully capture on their own. Meanwhile, emerging technologies in the field of artificial intelligence (AI), such as the performance of deep learning techniques in digital pathology, have garnered significant attention for their potential to be used in this space. Many have now turned their attention towards the immuno-oncology-related applications for digital pathology, particularly in analyzing whole-slide images of widely available H&E-stained slides to aid in immune biomarker detection and ICI response prediction. In this review, we discuss the current landscape of AI-based digital pathology in immuno-oncology, including its applications for identifying and measuring immune biomarkers and, importantly, its potential for predicting ICI response and survival outcomes. We will end by discussing the challenges and future directions of adopting AI technologies for clinical deployment.

Other0 citations2025-05-01Paper ->

203: IMPACT OF AGE ON EFFICACY AND SAFETY OF ADVANCED THERAPIES IN ULCERATIVE COLITIS: A POOLED ANALYSIS OF RANDOMIZED CONTROLLED TRIALS

Jaeyoun Choi, Dhruv Ahuja, GY Zou, S. Goodwin, V. Jairath et al.

Other184 citations2022-04-01Paper ->

Fine-Tuned DenseNet-169 for Breast Cancer Metastasis Prediction Using FastAI and 1-Cycle Policy

Adarsh Vulli, P. Srinivasu, Madipally Sai Krishna Sashank, J. Shafi, Jaeyoun Choi et al.

Lymph node metastasis in breast cancer may be accurately predicted using a DenseNet-169 model. However, the current system for identifying metastases in a lymph node is manual and tedious. A pathologist well-versed with the process of detection and characterization of lymph nodes goes through hours investigating histological slides. Furthermore, because of the massive size of most whole-slide images (WSI), it is wise to divide a slide into batches of small image patches and apply methods independently on each patch. The present work introduces a novel method for the automated diagnosis and detection of metastases from whole slide images using the Fast AI framework and the 1-cycle policy. Additionally, it compares this new approach to previous methods. The proposed model has surpassed other state-of-art methods with more than 97.4% accuracy. In addition, a mobile application is developed for prompt and quick response. It collects user information and models to diagnose metastases present in the early stages of cancer. These results indicate that the suggested model may assist general practitioners in accurately analyzing breast cancer situations, hence preventing future complications and mortality. With digital image processing, histopathologic interpretation and diagnostic accuracy have improved considerably.

Other1 citations2021-10-01Paper ->

A Twisted Elastic Rotary-Rail Actuator (TERRA) Using a Double-Stranded Helix Structure

Jae In Kim, Jaeyoun Choi, Junhyung Kim, Yong‐Lae Park

Robotics0 citations2021-09-22Paper ->

Pop-up cookie molds: self-folding elastomer sheets using thermal expansion of embedded air chambers

Junghan Kwon, Myungsu Park, Jaeyoun Choi, Yong‐Lae Park

Self-folding is a promising concept in the fields of smart materials and robotics, which allows self-assembly and multi-functionality. Although there have been approaches to realize self-folding mechanisms using different techniques, and their practical applications are not sufficiently investigated. Here, we propose untethered, self-folding polymer structures with embedded air chambers, which easily transform two-dimensional flat shapes into preprogrammed three-dimensional (3D) shapes when heat energy is transferred into the structures resulting in thermal expansion of the air chambers. This mechanism is particularly useful for casting materials that require shape and phase changes simultaneously if the proposed structures are used as molds. As a practical application, we present pop-up cookie molds that can bake 3D-shaped cookies from flat cookie dough. Analytical modelings based on the ideal gas law, the principle of minimum potential energy, and the lumped capacitance method for heat transfer are established and experimentally validated using prototypes. These provide a prediction of the structure’s bending curvature during the baking process. Furthermore, other target shapes, including bending, twisting, and their combinations, are also achieved by configuring various chamber designs. Finally, practical prototypes with more complex shapes are proposed, and their performances are demonstrated.

Other40 citations2021-08-01Paper ->

Assessing tumor heterogeneity: integrating tissue and circulating tumor DNA (ctDNA) analysis in the era of immuno-oncology - blood TMB is not the same as tissue TMB

S. Fridland, Jaeyoun Choi, M. Nam, S. Schellenberg, Eugene Kim et al.

Tissue tumor mutational burden (tTMB) is calculated to aid in cancer treatment selection. High tTMB predicts a favorable response to immunotherapy in patients with non-small cell lung cancer. Blood TMB (bTMB) from circulating tumor DNA is reported to have similar predictive power and has been proposed as an alternative to tTMB. Across many studies not only are tTMB and bTMB not concordant but also as reported previously by our group predict conflicting outcomes. This implies that bTMB is not a substitute for tTMB, but rather a composite index that may encompass tumor heterogeneity. Here, we provide a thorough overview of the predictive power of TMB, discuss the use of tumor heterogeneity alongside TMB to predict treatment response and review several methods of tumor heterogeneity assessment. Furthermore, we propose a hypothetical method of estimating tumor heterogeneity and touch on its clinical implications.

Other0 citations2021-05-01Paper ->

Metastatic CDK12-Mutated Neuroendocrine Tumor of Lung Showed an Exceptional Response to Olaparib and Paclitaxel.

W. Bae, J. Hwang, W. K. Hur, Jaeyoun Choi, M. Nam et al.

Other1 citations2020-11-01Paper ->

18 New method of assessing tumor heterogeneity utilizing both circulating tumor DNA and tissue DNA to predict the response to immunotherapy

Jaeyoun Choi, M. Nam, S. Fridland, J. Hwang, C. Jung et al.

Tumor heterogeneity assessment may help predict response to immunotherapy. In melanoma mouse models, tumor heterogeneity impaired immune response.1 In addition, among lung cancer patients receiving immunotherapy, the high clonal neoantigen group had favorable survival and outcomes.2 Ideal methods of quantifying tumor heterogeneity are multiple biopsies or autopsy. However, these are not feasible in routine clinical practice. Circulating tumor DNA (ctDNA) is emerging as an alternative. Here, we reviewed the current state of tumor heterogeneity quantification from ctDNA. Furthermore, we propose a new tumor heterogeneity index(THI) based on our own scoring system, utilizing both ctDNA and tissue DNA.Systematic literature search on Pubmed was conducted up to August 18, 2020. A scoring system and THI were theoretically derived.Two studies suggested their own methods of assessing tumor heterogeneity. One suggested clustering mutations with Pyclone,3 and the other suggested using the ratio of allele frequency (AF) to the maximum somatic allele frequency (MSAF).4 According to the former, the mutations in the highest cellular prevalence cluster can be defined as clonal mutations. According to the latter, the mutations with AF/MSAF<10% can be defined as subclonal mutations. To date, there have been no studies on utilizing both ctDNA and tissue DNA simultaneously to quantify tumor heterogeneity. We hypothesize that a mutation found in only one of either ctDNA or tissue DNA has a higher chance of being subclonal.We suggest a scoring system based on the previously mentioned methods to estimate the probability for a mutant allele to be subclonal. Adding up the points that correspond to the conditions results in a subclonality score (table 1). In a given ctDNA, the number of alleles with a subclonality score greater than or equal to 2 divided by the total number of alleles is defined as blood THI (bTHI) (figure 1). We can repeat the same calculation in a given tissue DNA for tissue THI (tTHI) (figure 2). Finally, we define composite THI (cTHI) as the mean of bTHI and tTHI.Abstract 18 Table 1Subclonality scoreAbstract 18 Figure 1Hypothetical distribution of all alleles found in ctDNA bTHI = the number of alleles with a subclonality score greater than or equal to 2/the total number of alleles found in ctDNA = 10/20 =50%Abstract 18 Figure 2Hypothetical distribution of all alleles found in tissue DNA tTHI= the number of alleles with a subclonality score greater than or equal to 2/the total number of alleles found in tissue DNA = 16/40 = 40% cTHI= (bTHI + tTHI)/2 = 45%Tumor heterogeneity is becoming an important biomarker for predicting response to immunotherapy. Because autopsy and multiple biopsies are not feasible, utilizing both ctDNA and tissue DNA is the most comprehensive and practical approach. Therefore, we propose cTHI, for the first time, as a quantification measure of tumor heterogeneity.Wolf Y, Bartok O. UVB-Induced Tumor Heterogeneity Diminishes Immune Response in Melanoma. Cell 2019;179:219–235.McGranahan N, Swanton C. Clonal neoantigens elicit T cell immunoreactivity and sensitivity to immune checkpoint blockade. Science 2016;351:1463–1469.Ma F, Guan Y. Assessing tumor heterogeneity using ctDNA to predict and monitor therapeutic response in metastatic breast cancer. Int J Cancer 2020;146:1359–1368.Liu Z, Xie Z. Presence of allele frequency heterogeneity defined by ctDNA profiling predicts unfavorable overall survival of NSCLC. Transl Lung Cancer Res 2019;8:1045–1050.

Other1 citations2020-11-01Paper ->

753 The immune landscape of papillary thyroid cancer and its association with neoantigen landscape and DNA repair gene mutations

M. Nam, Woojung Yang, J. Y. Lee, Jaeyoun Choi, Hansol Choi et al.

Tumors with high tumor mutational burden (TMB) or defects in mismatch repair (dMMR) respond well to immune checkpoint inhibitors (ICIs).1 2 TMB and DNA repair gene mutations including dMMR are closely related to the increase of neoantigens, which are recognized by immune cells to trigger an immune response.1 3 Although not a standard of care in thyroid cancer treatment, there are ongoing clinical trials for ICI use in differentiated thyroid carcinoma. However, not much has been explored concerning the neoantigen landscape and its association with immune traits in papillary thyroid cancer (PTC). We aim to analyze the immune landscape of PTC in association with neoantigen burden, TMB, and DNA repair gene mutations.We used the PTC cohort data from The Cancer Genome Atlas (TCGA). The mutation counts and data for neoantigen prediction were acquired from TCGA mutation calling. CloudNeo pipeline was used for neoantigen prediction. TMB was calculated as the sum of missense and indel mutation counts per megabase pairs covered by whole-exome sequencing. Tumor-infiltrating immune cells were estimated using CIBERSORT.Out of the 496 PTC patients from cBioPortal, a subset of 400 patients with available mutation counts and predicted neoantigen burden was included in the study. Immune cell infiltration estimated by CIBERSORT showed macrophage M2 as the most abundant, followed by macrophage M0 and other T cells (figure 1). The TMB ranged from 0.03 to 2.05 with a median value of 0.2. Neoantigen burden ranged from 0 to 18 with a median value of 1, which is relatively low compared to the median value of 18 in non-small cell lung cancer (NSCLC)1 (figure 2). One or more DNA repair gene mutations were discovered in 32 patients (8%). The mutation status of repair genes was not related to TMB or neoantigen burden. TMB or neoantigen burden was not related to immune traits such as infiltration of CD8+ T cells or regulatory T cells, cytolytic activity score, and PD-L1 expression.Abstract 753 Figure 1Immune cell infiltration estimated by CIBERSORTAbstract 753 Figure 2Histogram of neoantigen burdenThis is the first study to report the immune landscape of PTC in the context of neoantigen. The lack of association between TMB or neoantigen burden with immune traits may be due to the relatively low number of neoantigens in PTC compared to other immunogenic cancers such as NSCLC. Our results suggest that mutations in DNA repair genes or TMB are likely to have limited value in predicting response to ICI treatment in PTC.Chae YK, et al., Mutations in DNA repair genes are associated with increased neoantigen burden and a distinct immunophenotype in lung squamous cell carcinoma. Sci Rep 2019; 9:3235.Rizvi NA, et al., Cancer immunology. mutational landscape determines sensitivity to PD-1 blockade in non-small cell lung cancer. Science 2015; 348:124–128.Schumacher TN, Schreiber RD, Neoantigens in cancer immunotherapy. Science 2015; 348:69–74.

Other0 citations2020-11-01Paper ->

752 The impact of grade of differentiation and BRAF mutation status on neoantigen and immune landscape in papillary thyroid cancer

M. Nam, Woojung Yang, J. Y. Lee, Jaeyoun Choi, Hansol Choi et al.

Background The use of immune checkpoint inhibitors (ICIs) in cancer treatment has been approved by the FDA, but its application is experimental in the treatment of papillary thyroid cancer (PTC). Induction of immune response via recognition of neoantigens is considered to be the basis for the treatment mechanism of ICIs.1 However, the neoantigen landscape has not been explored in PTC. Our aim is to investigate the immune landscape of PTC in relation to neoantigens, taking into account the BRAF mutation status and grade of differentiation as contributing factors. Methods BRAF V600E mutation status and thyroid differentiation scores (TDSs) were gathered from the PTC cohort of The Cancer Genome Atlas (TCGA). TDS was derived from the mRNA expression levels of 16 thyroid function genes to quantify the grade of differentiation. Tumors with TDSs in the 1st quartile and 4th quartile were defined as poorly differentiated and well differentiated, respectively. The neoantigen burden for each sample was predicted using CloudNeo pipeline. The infiltration of immune cells was calculated through CIBERSORT. Results Among 400 patients with predicted neoantigen data, 187 (47%) had BRAF mutations. The BRAF mutated tumors showed increased cytolytic activity score (CYT, p=0.001), increased infiltration of regulatory T cells (Treg, p Conclusions Increased CYT and higher expression of PD-L1 in the BRAF mutated or the poorly differentiated tumors imply the possible role of ICI use in these subgroups of patients. However, the immune response to these subgroups does not seem to be mediated through the increase in neoantigen formation. Further studies are warranted to explore markers for immunotherapy implication. References Schumacher TN, Schreiber RD, Neoantigens in cancer immunotherapy. Science 2015; 348:69–74.

Other40 citations2020-10-21Paper ->

Overcoming acquired resistance to PD-1 inhibitor with the addition of metformin in small cell lung cancer (SCLC)

Yeseul Kim, E. Vagia, P. Viveiros, C. Kang, J. Y. Lee et al.

Other0 citations2020Paper ->

THE IMPACT OF GRADE OF DIFFERENTIATION AND BRAF MUTATION STATUS ON NEOANTIGEN AND IMMUNE LANDSCAPE IN PAPILLARY THYROID CANCER

Y. Lee, Jaeyoun Choi, Hansol Choi, Emma P K Yu, Eugene Kim et al.

Learning0 citations2015-10-31Paper ->

A Numerical Study on the Reinforcement Method of a Pillar Using Tension Bolts at the Connecting Part between 2-Arch Tunnels and Parallel Tunnels

Yeonjun Park, Jaeyoun Choi

Abstract Two-arch tunnels require minimal spacing between the 2 tunnels and thus occupy small amount of land compared to parallel tunnels. But it is rather expensive. The parallel tunnel is not as expensive, but it requires more land than 2-arch tunnels. This may cause a problem when there is a land shortage. The new design is to connect these two types of tunnels by another pair of parallel tunnels where the separation distance is gradually increasing. The applicability of this new design to the cases where rock condition is not even fair has to be verified since the width of the pillar between the connecting tunnels can be quite narrow. Therefore both two and three dimensional numerical analyses were conducted and pillar stability was examined for rock classes IV and V in two different ways. Results showed that this new design is still effective for poor rock conditions if central pillar is properly reinforced by tension bolts as long as overburden is less than five times of the tunnel diameter.Key words 2-arch tunnel, Parallel tunnel, Pillar 2-arch varying section tunnel, Tension bolt초 록 2-아치 터널은 터널의 간격이 매우 좁아서 병렬 터널에 비해 점유 면적이 작으나 경제적이지 못하다 . 병렬 터널은 경제적이긴 하지만 2-아치 터널보다 점유 면적이 커서 용지의 매입이 어려운 경우에는 문제가 될 수 있다. 새로운 설계는 이 두 터널을 터널의 간격이 점차 증가하는 제 3의 병렬터널로 연결시키는 것이다. 접속 터널의 필라는 폭이 매우 좁을 수 있기 때문에 이 새로운 설계를 불량한 암반에 적용하려면 검증이 필요하다 . 이에 4등급 및 5등급 암반에 대해 2차원 및 3차원 수치해석을 이용하여 2가지 방법으로 안정성 검토를 수행하였다. 검토 결과, 중앙 필라가 텐션 볼트로 적절히 보강된다면 터널 심도가 직경의 5배 이하인 경우에는 적용이 가능하였다.핵심어 2-아치 터널, 병렬 터널, 2-arch 변단면 터널, 필라, 텐션 볼트

Other2 citations2012-10-31Paper ->

A Case Study on the Design and Construction of a 2-arch Tunnel with Varying Section

Jaeyoun Choi, Yeonjun Park, Si-Keun Kim, Jae-Hyun Park

Other3 citations2003-06-30Paper ->

Docetaxel and Cisplatin Combination Chemotherapy in Patients with Squamous Cell Carcinomas of the Head and Neck.

Jung Hyun Lee, K. Lee, Young-jin Choi, Jaeyoun Choi, H. Shin et al.

CBF Related Papers
Robotics0 citations2026-07-22arXiv ->

Safe and Scalable Multi-Drone Payload Transport via CBF-based Reinforcement Learning with Zero-Shot Sim-to-Real Transfer

Jaeyoun Choi, Oswin So, Songyuan Zhang, Cooper Taylor, Chuchu Fan

Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster response. However, the complex coupled dynamics among drones, cables, and payloads pose significant challenges, and existing approaches remain limited in safety and scalability, particularly in dynamic and unstructured environments. In this work, we propose a learning-based framework for safe and scalable multi-drone cooperative payload transport. We introduce a minimal 2D abstraction that preserves the task-relevant drone-payload coupling required for coordination and safety, while remaining computationally efficient for large-scale learning. Using domain randomization over team size and physical parameters, we train a fully distributed policy via Discrete Graph Control Barrier Function Proximal Policy Optimization (DGPPO), enabling robust zero-shot sim-to-real transfer without fine-tuning. Extensive real-world evaluations demonstrate that a single learned policy generalizes across varying team sizes and task scenarios. Furthermore, multi-group hardware experiments show that the same policy can safely operate in dynamic environments, where other drone teams act as moving obstacles. These results indicate that the proposed framework enables efficient, safe, and scalable multi-drone payload transportation with strong generalization to complex real-world conditions.

CBF Related Papers
Robotics0 citations2026-07-22arXiv ->

Safe and Scalable Multi-Drone Payload Transport via CBF-based Reinforcement Learning with Zero-Shot Sim-to-Real Transfer

Jaeyoun Choi, Oswin So, Songyuan Zhang, Cooper Taylor, Chuchu Fan

Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster response. However, the complex coupled dynamics among drones, cables, and payloads pose significant challenges, and existing approaches remain limited in safety and scalability, particularly in dynamic and unstructured environments. In this work, we propose a learning-based framework for safe and scalable multi-drone cooperative payload transport. We introduce a minimal 2D abstraction that preserves the task-relevant drone-payload coupling required for coordination and safety, while remaining computationally efficient for large-scale learning. Using domain randomization over team size and physical parameters, we train a fully distributed policy via Discrete Graph Control Barrier Function Proximal Policy Optimization (DGPPO), enabling robust zero-shot sim-to-real transfer without fine-tuning. Extensive real-world evaluations demonstrate that a single learned policy generalizes across varying team sizes and task scenarios. Furthermore, multi-group hardware experiments show that the same policy can safely operate in dynamic environments, where other drone teams act as moving obstacles. These results indicate that the proposed framework enables efficient, safe, and scalable multi-drone payload transportation with strong generalization to complex real-world conditions.

CBF Related Papers
Robotics0 citations2026-07-22arXiv ->

Safe and Scalable Multi-Drone Payload Transport via CBF-based Reinforcement Learning with Zero-Shot Sim-to-Real Transfer

Jaeyoun Choi, Oswin So, Songyuan Zhang, Cooper Taylor, Chuchu Fan

Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster response. However, the complex coupled dynamics among drones, cables, and payloads pose significant challenges, and existing approaches remain limited in safety and scalability, particularly in dynamic and unstructured environments. In this work, we propose a learning-based framework for safe and scalable multi-drone cooperative payload transport. We introduce a minimal 2D abstraction that preserves the task-relevant drone-payload coupling required for coordination and safety, while remaining computationally efficient for large-scale learning. Using domain randomization over team size and physical parameters, we train a fully distributed policy via Discrete Graph Control Barrier Function Proximal Policy Optimization (DGPPO), enabling robust zero-shot sim-to-real transfer without fine-tuning. Extensive real-world evaluations demonstrate that a single learned policy generalizes across varying team sizes and task scenarios. Furthermore, multi-group hardware experiments show that the same policy can safely operate in dynamic environments, where other drone teams act as moving obstacles. These results indicate that the proposed framework enables efficient, safe, and scalable multi-drone payload transportation with strong generalization to complex real-world conditions.

  • Robotics35
  • Systems and Control31
  • Optimization and Control11
  • Machine Learning5
  • cs.MA3
  • Artificial Intelligence2
  • Computer Vision and Pattern Recognition1
  • Dynamical Systems1
  • quant-ph1
Robotics | 35 papers | 56.5% coverage
Robotics0 citations2026-07-22arXiv ->

Safe and Scalable Multi-Drone Payload Transport via CBF-based Reinforcement Learning with Zero-Shot Sim-to-Real Transfer

Jaeyoun Choi, Oswin So, Songyuan Zhang, Cooper Taylor, Chuchu Fan

Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster response. However, the complex coupled dynamics among drones, cables, and payloads pose significant challenges, and existing approaches remain limited in safety and scalability, particularly in dynamic and unstructured environments. In this work, we propose a learning-based framework for safe and scalable multi-drone cooperative payload transport. We introduce a minimal 2D abstraction that preserves the task-relevant drone-payload coupling required for coordination and safety, while remaining computationally efficient for large-scale learning. Using domain randomization over team size and physical parameters, we train a fully distributed policy via Discrete Graph Control Barrier Function Proximal Policy Optimization (DGPPO), enabling robust zero-shot sim-to-real transfer without fine-tuning. Extensive real-world evaluations demonstrate that a single learned policy generalizes across varying team sizes and task scenarios. Furthermore, multi-group hardware experiments show that the same policy can safely operate in dynamic environments, where other drone teams act as moving obstacles. These results indicate that the proposed framework enables efficient, safe, and scalable multi-drone payload transportation with strong generalization to complex real-world conditions.

Robotics0 citations2026-07-22arXiv ->

Distributed Motion Planning with Safety Guarantees for Self-Reconfiguring Robotic Boats

Alejandro Gonzalez-Garcia, Wei Wang, Wei Xiao, Wilm Decre, Jan Swevers et al.

Aquatic self-reconfigurable robots must assemble into desired shapes while ensuring safe interactions among multiple agents. This paper proposes a hybrid framework that combines distributed Model Predictive Control (MPC) with Control Barrier Functions (CBFs) for multi-agent shape formation and reconfiguration. Given a desired shape and target assignment, a distributed MPC scheme, solved via the Alternating Direction Method of Multipliers (ADMM), computes coordinated trajectories through local optimization and information exchange. To ensure safety in real time, distributed CBF-based filters are applied to enforce inter-agent collision avoidance. The proposed approach leverages the predictive capabilities of MPC to mitigate local minima, while CBFs provide formal safety guarantees despite the nonconvexity of the underlying optimization problem. Simulation results with up to 25 agents and experimental validation with four physical robots demonstrate the effectiveness and scalability of the framework.

Robotics0 citations2026-07-21arXiv ->

Learning Personalized Safety Interventions for Haptic Human-Robot Shared Control

Dawei Zhang, Roberto Tron

Haptic feedback provides an implicit channel for communicating safety intentions during human-robot shared control. Existing haptic guidance systems typically employ predefined intervention strategies that cannot accommodate the diverse safety preferences of individual users or application scenarios. To address this limitation, we propose a Learning from Haptics (LfH) framework that learns user-preferred safety interventions from sparse demonstrations, eliminating the need for manual trial-and-error design. Our framework is built on a differentiable Control Barrier Function (CBF)-based optimization layer that automatically adjusts the underlying safety parameters to match the demonstrated haptic responses. Instead of tuning controller parameters directly, users teach the system how they expect it to intervene during teleoperation. The resulting haptic guidance reflects the demonstrated intervention preferences while preserving the intuitive interaction of haptic shared control. Simulation and hardware experiments demonstrate that the proposed framework can learn personalized safety interventions from sparse user input and reduce the mismatch between the generated haptic feedback and the demonstrated preferences.

MPC/Planning0 citations2026-07-21arXiv ->

Pose-Parameterized Motion Planning and CBF-QP Self-Collision Filtering for a Long-Reach Drilling Boom

Mehdi Heydari Shahna, Tuomo Kivelä, Jouni Mattila

Long-reach drilling booms must reach successive poses without self-collision. Moving from operator-supervised control toward autonomy requires collision-aware motion planning and execution. For the Sandvik SB60, this study adapts established methods by integrating pose-parameterized planning with a capsule-based control barrier function quadratic program (CBF-QP) in measured-state inverse kinematics (IK). A fixed task-specific parameter set within each task generates waypoints, detours, timed references, and chained motion without target-specific retuning. The offline detour planner screens candidate waypoints using 23 selected rod-segment-to-body-region distances, whereas the online CBF-QP filters joint velocities using 14 configured capsule-pair constraints from a nine-primitive whole-body capsule model. Evaluation considers two drilling tasks in a manufacturer-developed SB60 Simscape Multibody model: a five-target restricted-orientation tour and a three-target full-pose tour. Across several hundred thousand samples, the method produced zero IK failures, generated several detour waypoints, achieved millimetre-level mean final-position error, and recorded no sampled CBF margins below the reported thresholds.

Theory0 citations2026-07-19arXiv ->

Optimal Safety Control using High-Order Control Barrier Functions

Neng Li, Zuodong Pan, Jiaxing Wang, Weiguo Xia, Wei Ren

This paper investigates the optimal safety control problem of nonlinear control systems by proposing novel high-order control barrier functions (HOCBFs). Different from zeroing HOCBFs, two novel HOCBFs are derived and the safety controllers are designed in an explicit way. Next, we implement vector Lyapunov function approach to propose a novel high-order control Lyapunov function (HOCLF) for the stabilization control problem. The relations between the proposed and existing HOCBFs are discussed. Afterwards, the compatibility of the proposed HOCLF and HOCBF is addressed to guarantee the stabilization and safety control objectives simultaneously, and thus the optimal controller is established. Finally, a numerical example from the navigation problem of quadrotors is presented to illustrate the efficacy of the derived results.

Robotics0 citations2026-07-18arXiv ->

ADMM-Based Safety-Critical Distributed NMPC for Cooperative Transportation by Quadrupedal Robots

Ruturaj S. Sambhus, Kapi Ketan Mehta, Yicheng Zeng, Kaveh Akbari Hamed

This paper presents a safety-critical distributed nonlinear model predictive control (DNMPC) framework for cooperative payload transportation by teams of quadrupedal robots. The proposed approach models the robotic team and the shared payload as a dynamically coupled networked system with rigid holonomic coupling constraints arising from cooperative transportation. To enable distributed real-time optimization, the centralized finite-horizon optimal control problem is decomposed into parallel local NMPC subproblems coordinated through the alternating direction method of multipliers (ADMM). The resulting distributed framework enforces consensus over both payload-state and interaction-wrench trajectories while explicitly incorporating acceleration-level holonomic coupling constraints within the distributed predictive control formulation. Safety-critical obstacle avoidance constraints for both the robotic agents and payload are enforced using higher-order control barrier functions (HOCBFs). The framework is validated through numerical simulations with teams of two, three, and four quadrupedal robots transporting shared payloads in cluttered environments. Real-time experiments on two- and three-robot teams demonstrate safe and robust transportation under payload uncertainty and external disturbances. Compared with centralized NMPC, the proposed framework achieves up to 23% reduction in average NLP solve time while maintaining comparable closed-loop performance. Ablation studies further demonstrate robustness to communication delays and show that explicit payload-state consensus and holonomic constraints substantially improve payload tracking and distributed coordination over existing wrench-only consensus formulations.

Robotics0 citations2026-07-18arXiv ->

AI-Augmented Model Predictive Control for Safe and Adaptive Rendezvous and Proximity Operations

Luca Sportelli, Tyler Barr, Cagri Kilic, Di Wu

Autonomous rendezvous and proximity operations (RPO) in adversarial orbital environments require guidance architectures balancing target pursuit, safety preservation, and real-time adaptability under dynamically evolving interaction conditions. Although learning-based approaches show promise, their application to safety-critical orbital robotics remains limited by concerns regarding interpretability, robustness, and constraint awareness. This work presents an adaptive Model Predictive Control (MPC) framework for autonomous spacecraft RPO in multi-agent adversarial scenarios. The proposed architecture combines a constrained receding-horizon MPC formulation with a data-driven supervisory tuning layer that adjusts controller parameters from offline closed-loop evaluation and online interaction geometry. Relative motion follows Clohessy-Wiltshire (CW) dynamics, enabling computationally efficient finite-horizon prediction and real-time quadratic optimization. The MPC formulation incorporates actuator limits, predictive keep-out-zone constraints, slack-variable feasibility handling, and optional Control Barrier Function (CBF) safety filtering. Rather than generating thrust commands directly, the adaptive layer modifies interpretable MPC parameters, including tracking weights, safety penalties, minimum-separation objectives, and keep-out-zone objectives. The framework was evaluated in the official Kerbal Space Program Differential Game (KSPDG) Capture-the-Satellite environment through Monte Carlo simulations. Results demonstrate improved closed-loop robustness, adaptive maneuvering behavior, and rendezvous performance compared with fixed-parameter MPC while preserving safety-aware operation and real-time feasibility, providing a modular, interpretable foundation for adaptive spacecraft RPO.

Robotics0 citations2026-07-17arXiv ->

Certifiable Safe Model-Based Reinforcement Learning with Control-Affine Dynamics Approximation

Hao Zhou, Yanze Zhang, Cameron Reid, Wenhao Luo

Safe model-based reinforcement learning (RL) often bridges control-theoretic analysis and RL for robots to safely explore (partially) unknown system dynamics while deriving control actions for task efficiency. The control performance and safety assurance typically rely on prior knowledge of partially modeled nominal system dynamics and the data-driven models that compensate for residual model uncertainties. However, existing methods often overlook the structure of residual model uncertainties (e.g., components affine in control), which could lead to overly conservative robot behaviors or invalid safety guarantees under the safe learning-based controllers. This paper proposes a safe reinforcement learning framework that learns control-affine dynamics with a certifiable data-driven safe policy using control barrier functions (CBF). Specifically, we first use Control-Affine Random Fourier Features (ARFF) to model robot dynamics in a control-affine form, which offers computational efficiency that scales with dataset size and reduces potential model bias for model-based reinforcement learning. Then, a model-free, efficient uncertainty quantification method using adaptive conformal prediction (ACP) is applied to quantify the uncertainty in the safety constraint arising from the learned control-affine dynamics. This allows for data-driven safety assurance amenable to principled and efficient controller synthesis with CBF. Simulation results on the cartpole and the 3D quadrotor platforms demonstrate the effectiveness of the proposed framework.

Robotics0 citations2026-07-16arXiv ->

Risk-Aware Belief Control Barrier Functions over Random Finite Sets

Shaohang Han, Gang Chen, Yixi Cai, Ignacio Torroba, Ivan Stenius et al.

Ensuring robot safety in unknown, dynamic environments is a fundamental requirement. It involves inferring the states of an unknown and time-varying number of moving objects from noisy, incomplete measurements. We address safe control under the induced multi-object state uncertainty with a risk-aware belief control barrier function (BCBF) framework. The uncertainty is captured by a random finite set (RFS) belief, estimated by a sequential Monte Carlo probability hypothesis density (SMC-PHD) filter that represents it with a set of particles. Building directly on these particles, we construct a nonsmooth BCBF, establish forward invariance of the safe set under continuous prediction, and derive an explicit condition under which discrete updates preserve safety. Simulation and real-world underwater experiments demonstrate the effectiveness and efficiency of the proposed approach.

Robotics0 citations2026-07-16arXiv ->

Safe Execution of RL Policies Via Acceleration-Based CBF-QP Constraint Enforcement for Real-World Robotic Deployments

Bastien Muraccioli, Alice Cariou, Pierre-Alexandre Leziart, Mathieu Celerier, Arnaud Demont et al.

Reinforcement Learning (RL) has demonstrated remarkable capabilities for solving complex robotic control problems, but its lack of safety guarantees severely limits deployment on hardware. In particular, as legged robots and manipulators often operate near safety-critical boundaries, out-of-distribution states can lead to failure upon deployment. To address this, we introduce Acc-CBF-QP, an acceleration-based Quadratic Program (QP) safety filter using Control Barrier Functions (CBFs) that constrains any RL policy onto a safe set at runtime without modifying training. The method applies to unconstrained and Safe-RL policies, and enforces joint position, velocity, torque, and collision constraints within a unified optimization framework. A key contribution is the formulation of RL+QP tasks that regulate deviation from the RL command when constraints would otherwise be violated. We introduce a TorqueTask, minimizing torque deviation, and a Forward Dynamics Task, minimizing induced acceleration deviation, thus providing principled control over safety-performance trade-offs. Experiments on a 7-DoF Kinova Gen3 manipulator and a 19-DoF Unitree H1 humanoid, both in simulation and on hardware, highlight substantial reductions in constraint violations. On the real H1 hardware, a Safe-RL policy alone yielded 10.04 violations/s, which were reduced by 92% to 0.80 violations/s when augmented with Acc-CBF-QP. On the Kinova Gen3, Acc-CBF-QP fully eliminated violations. Nominal task performance of the RL objective is preserved in violation-free regimes. Under aggressive velocity commands on H1, Acc-CBF-QP improves execution by preventing constraint-induced shutdowns, yielding longer survival times. The full pipeline is open-source.

MPC/Planning0 citations2026-07-15arXiv ->

Discriminative Barrier Functions for Safe Adversarial Imitation Learning from Observation

Anubhav Vishwakarma, Bhaumik Mehta, Caleb Hsu, Byron Boots, Karen Leung et al.

Inverse Reinforcement Learning (IRL) algorithms are powerful tools for learning from and generalizing expert demonstrations, but they often rely on unconstrained exploration, rendering them unsafe for real-world deployment. Meanwhile, Control Barrier Functions (CBFs) can guarantee the safety of control systems, but the analytical design of CBFs can be time-consuming and esoteric. In this work, we address these limitations jointly by constraining reward function candidacy during IRL to the space of CBFs, yielding a formulation that exhibits safe online control with continuous experiential improvement. Crucially, this framework enables the data-driven recovery of barrier functions directly from unlabeled expert observations. We demonstrate that the recovered barrier function is robust to unsafe states entirely absent from the expert data. Furthermore, we benchmark our method against standard IRL baselines in a simulated navigation environment, demonstrating improved safety performance. Finally, we investigate the trade-offs of planning-based versus policy-based IRL methods across both simulation and a real world obstacle avoidance task.

Robotics0 citations2026-07-15arXiv ->

Safe Overtaking for Autonomous Racing Using Hierarchical Optimization and Learning-Based Control

Hassan Jardali, Kai Yin, Lantao Liu

Autonomous racing overtaking requires balancing competitive performance with safety under nonlinear vehicle dynamics and real-time constraints. Model Predictive Control (MPC) combined with Control Barrier Functions (CBFs) provides a principled mechanism for certifying forward invariance of a safe set. However, commonly used fixed-decay discrete-time CBF formulations can become overly conservative in interactive racing scenarios, limiting overtaking performance and requiring manual tuning across track conditions. This paper proposes a hierarchical overtaking framework that explicitly separates maneuver-level decision making from safety-certified trajectory control, reducing conservatism while preserving safety. A high-level Mixed-Integer Quadratic Program (MIQP) resolves the combinatorial passing-side selection problem by selecting a feasible overtaking topology, while a nonlinear Frenet-frame MPC enforces vehicle dynamics and safety through embedded discrete-time CBF constraints. This decomposition isolates the combinatorial complexity of maneuver selection from the continuous trajectory optimization. To further mitigate the sensitivity of fixed-decay barrier constraints, a reinforcement learning policy adapts the discrete-time CBF decay parameter online, enabling context-dependent modulation of safety margins without directly controlling vehicle inputs. Simulation and scaled-hardware experiments show that no single fixed decay parameter achieves uniformly strong performance across tracks, whereas the adaptive strategy attains the highest aggregate success rate and consistently strong safety--performance trade-offs without per-track tuning, improving robustness to environment variation while maintaining safety constraint satisfaction in nominal operation.

Robotics0 citations2026-07-14arXiv ->

Autonomous Tracking and Terminal Guidance of Moving Targets for Fixed-Wing UAVs

Wei-Hao Liou, Teng-Hu Cheng

This study introduces a unified control framework for fixed-wing unmanned aerial vehicles (UAVs) fitted with a pan-tilt (PT) camera, intended to perform an end-to-end mission spanning from initial target detection to accurate terminal engagement. The proposed system employs a three-phase strategy: a vision-based target acquisition phase, an NMPC-based tracking phase, and a terminal guidance phase. During tracking, the framework uses an Unscented Kalman Filter (UKF) to fuse YOLO-based visual detections with inertial measurements, enabling robust target state estimation under unknown dynamics. To ensure reliable visual contact, we introduce a constraint-aware Nonlinear Model Predictive Control (NMPC) strategy that incorporates Control Barrier Functions (CBFs) to explicitly prevent UAV self-occlusion -- a common limitation in fixed-wing tracking. Upon satisfying terminal engagement conditions, the system seamlessly transitions control to a quaternion-based Biased Proportional Navigation Guidance (BPNG) law, enforcing precise impact angle constraints. High-fidelity simulations demonstrate that the framework achieves stable, robust tracking and accurate terminal interception while strictly respecting the vehicle's dynamic limits and camera field-of-view constraints.

Robotics0 citations2026-07-14arXiv ->

Model-Based Diffusion Optimal Control for Multi-Robot Motion Planning

Zhilin He, Yorai Shaoul, Jiaoyang Li

Multi-Robot Motion Planning in continuous environments, where robots must generate dynamically feasible, collision-free trajectories, is challenging due to the combinatorial growth of the joint trajectory space and the difficulty of enforcing dynamic feasibility and hard safety constraints. Recent approaches recast trajectory planning as probabilistic inference, sampling from a posterior over trajectories using diffusion models whose score functions are learned from demonstration data. While showing promising performance, these approaches are limited: they often rely on sizable demonstration datasets and struggle to rigorously enforce dynamics and hard safety constraints during sampling. To this end, we introduce Model-Based Diffusion Optimal Control (MDOC), a model-based diffusion planner that efficiently produces dynamically feasible trajectories without relying on data. Crucially, we show that MDOC's safety mechanism -- combining known dynamics models with Control Barrier Function-constrained projections -- naturally scales to multi-robot planning settings through Conflict-Based Search. Across simulation experiments, this integrated method consistently outperforms representative baseline planners in sample efficiency, geometric smoothness, and success rate, while reducing computation time and producing collision-free trajectories.

Robotics0 citations2026-07-12arXiv ->

D-SafeMPC: Diffusion-Driven Safe Model Predictive Control with Discrete-Time Control Barrier Functions

Erdi Sayar, Ersin Daş, Joel W. Burdick, Alois Knoll, Erdal Kayacan

A key limitation on the use of diffusion models in robotic planning is their inability to inherently enforce safety or dynamical constraints, which often results in physically infeasible or unsafe outputs. Hybrid approaches that employ model predictive control (MPC) to address this problem can be unstable, as poor trajectory initializations from the diffusion model prevent the MPC from converging to a safe and feasible solution. To overcome these challenges, we propose D-SafeMPC, which enhances the interaction between diffusion and control. Our method guides the reverse diffusion process with control barrier functions (CBFs) and control Lyapunov functions (CLFs) and employs an iterative-projection scheme where an MPC refines the trajectory at each denoising step. This steers sampling toward safe, goal-directed regions and provides reliable MPC warm starts. In simulations on a Franka manipulator across four scenarios (one static-obstacle and three dynamic-obstacle settings) and in a sim-to-real experiment on a physical Franka robot, D-SafeMPC improves safety, task success rates, and planning efficiency over state-of-the-art baselines. To facilitate reproducibility, our source code and experimental configurations are available in a repository at https://github.com/erdiphd/D-SafeMPC

Learning0 citations2026-07-10arXiv ->

Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation

Alex Zongo, Peng Wei

Learning-based separation assurance for small Unmanned Aircraft Systems (sUAS) achieves near-zero collision rates in simulation, but assumes accurate position and velocity information from Global Navigation Satellite Systems (GNSS). This assumption fails in urban environments, where multipath propagation, signal blockage, and intentional interference degrade navigation integrity. This raises a fundamental architectural question for deploying learned separation policies under GNSS degradation: should runtime safety mechanisms filter the policy's actions or its observations? This work evaluates both approaches for multi-agent sUAS separation under adversarial GNSS degradation. Both architectures first estimate a worst-case traffic state consistent with bounded observation uncertainty, then diverge: action filtering constrains policy outputs via discrete-time control barrier functions evaluated at the worst-case state, while observation filtering presents the worst-case state directly to the policy as corrected input. Experimental results show that action filtering provides negligible safety improvement, while observation filtering reduces near mid-air collisions by 90% and remains robust to the barrier function's tradeoff between separation distance and closing rate. These results suggest that, for policies with learned safety behaviors, preserving the policy's decision authority outperforms overriding its actions with hand-designed constraints.

Robotics0 citations2026-07-10arXiv ->

SEAMLiS: Visibility-Aware Safety for Perception-Limited Multi-Robot Exploration

Taekyung Kim, Rahul H Kumar, Aswin D. Menon, Tzu-Hsiang Lin, Dimitra Panagou

Autonomous exploration in unknown environments is typically driven by informative frontiers, viewpoints, or trajectories, while local safety controllers avoid obstacles represented in the current map. Under finite sensing range and limited field of view, this separation can be unsafe: an exploration stack may plan optimistically through unobserved space and steer the sensor toward information gain rather than along the direction of motion, causing hidden obstacles to be detected too late for bounded-actuation avoidance. This paper presents SEAMLiS (Safe Exploration for Autonomous Multi-Robot Systems Under Limited Sensing), a modular execution-layer safety framework for decentralized multi-robot exploration. SEAMLiS preserves the upstream exploration stack, including the goal allocator and local planner, and enforces safety at the execution layer through perception-aware attitude and positional filters. A gatekeeper-based attitude filter switches between a visibility-promoting yaw policy and a velocity-tracking backup policy to preserve visibility of the critical known-free/unknown boundary with sufficient braking margin. A Control Barrier Function (CBF)-based positional filter then avoids known obstacles, newly detected obstacles, and other robots. We provide sufficient collision-avoidance conditions and validate the framework in randomized simulation, Isaac Sim, and Crazyflie hardware experiments. Results show collision-free exploration across tested single- and multi-robot settings while retaining much of the efficiency of visibility-promoting yaw control.

Robotics0 citations2026-07-09arXiv ->

SplatCtrl: Perception-Action Coupling via Gaussian Scene Representations and Reactive Robot Control

Siddarth Jain, Ho Jin Choi

Robotic manipulators excel in structured environments but face substantial challenges in unstructured and dynamic settings. This paper presents SplatCtrl, a unified framework for real-time scene reconstruction and reactive robot motion generation to enable collision-free robotic arm control in previously unseen and continuously changing environments. Building on 3D Gaussian Splatting (3D-GS), we introduce a hybrid voxel-based filtering and dynamic Gaussian relocation strategy that supports efficient scene reconstruction from RGB-D streams while accommodating environmental changes. For safe and reactive control, we further propose a method for deriving continuous signed distance functions from isotropic Gaussians, providing stable and differentiable collision probability estimates that bridge classical distance fields with the modern implicit representation. These continuous distance metrics are incorporated into control barrier functions, resulting in a unified perception-action coupling framework that supports smooth and reliable real-time motion generation in response to scene changes. Experimental validation in simulation, on physical robot, and within shared human-robot workspace demonstrates the framework's effectiveness, achieving integrated scene reconstruction and reactive control in uncertain, and dynamic environments.

Robotics0 citations2026-07-01arXiv ->

Robust Operational Space Control with Conformal Disturbance Bounds for Safe Redundant Manipulation

Wenhua Liu, Fan Zhang, Qin Lin

Redundant robotic manipulators operating in constrained and human-interactive environments require accurate task-space tracking together with rigorous safety guarantees under dynamic uncertainties. Classical operational space computed torque controller (OSCTC) relies on accurate dynamic models and degrades in the presence of disturbances. In contrast, the data-driven paradigm of residual learning approximates disturbances as functions learned from full-state measurements, which are often noisy in practice, lack rigorous theoretical guarantees, and introduce additional design complexity. This paper proposes a robust OSCTC framework that integrates an extended state observer (ESO) with conformal prediction to combine model-based robustness and data-driven adaptability. The ESO estimates lumped disturbances directly in operational space without requiring full-state measurements as in residual learning, and a robust control barrier function (CBF) is constructed to enforce safety under uncertainty. However, robust CBFs require a known disturbance-variation bound to guarantee absolute safety, which often leads to conservatism in practice. To address this limitation, we further employ a sliding-window conformal prediction mechanism to estimate the bound online in a distribution-free manner, thereby achieving practical probabilistic safety guarantees. Experiments on a 7-DoF Franka Research 3 manipulator demonstrate millimeter-level tracking accuracy and real-time safe control at 1~kHz under various disturbances.

Robotics0 citations2026-06-23arXiv ->

Causality-Based Parametric Control Barrier Function for Safe Multi-Vehicle Interaction

Yiwei Lyu, Caleb Chang, John M. Dolan

Safe control has been widely studied in various safety-critical applications, for instance, autonomous driving. In order to ensure the autonomous vehicle does not collide with other vehicles, it is essential to obtain an accurate expectation of surrounding vehicles' behavior and react adaptively. Instead of assuming fully cooperative and homogeneous vehicles using the same safety-critical controllers, recent works have been exploring different data-driven approaches to model the neighboring vehicles' underlying controllers with observed data. However, existing works either suffer from 1) the inter-vehicle influence during the multi-vehicle interaction, which makes it hard to determine the causality of surrounding vehicles' behavior in controller modeling, or 2) being dominated by the worst-case analysis, which may lead to overly conservative behavior. In this paper, we extend the prior work on Parametric-Control Barrier Function (Parametric-CBF) to multi-robot interactions with embedded causality inference to explicitly reason over the inter-vehicle influence. Given the learned Causality-based Parametric-CBF, we present an adaptive safety-critical controller that allows the ego vehicle to safely react to surrounding vehicles with the learned expectation. We demonstrate that by leveraging the motion flexibility among multi-vehicle systems, task efficiency can be greatly improved in various interaction-intensive scenarios.

Learning0 citations2026-06-20arXiv ->

Decentralized Geometric Control for Cable-Suspended Payload Transport with Adaptive Mass Estimation

Hadi Hajieghrary, Benedikt Walter, Paul Schmitt, Miguel Hurtado

Cooperative aerial transport requires controllers that respect nonlinear manifold geometry, operate without centralized coordination, and respect operational safety constraints. To address these demands, we present GPAC, a four-layer hierarchical architecture that enables $N$ quadrotors to transport a cable-suspended payload without a central coordinator or by exchanging cable states or adaptive parameters. The key insight is implicit coordination: each quadrotor independently estimates its effective load share from local cable measurements, so combined forces converge to the correct total, even without knowledge of $N$ or the payload mass; the payload position is reconstructed locally from each agent's own cable geometry, and the only inter-agent communication is a low-rate neighbor-position broadcast for collision avoidance. GPAC operates directly on the full nonlinear configuration manifold and integrates geometric position and attitude control, anti-swing regulation, an extended-state observer for wind rejection, concurrent learning-based mass estimation without persistent excitation, and a priority-ordered control barrier function (CBF)-inspired safety filter that reduces operational risk, with input-to-state safety (ISSf) margins that hold exactly under single-constraint activation. A compatibility result shows that the filter's force modifications keep the desired attitude within the almost-global stability region of the $\mathrm{SO}(3)$ attitude controller. Finally, high-fidelity simulation with flexible cables, onboard sensor fusion, and wind turbulence -- with all control and estimation loops closed through the estimator -- yields a mean payload-tracking RMSE of 33.8 cm (2.8\% coefficient of variation over 13 seeds) at a low per-agent computational cost.

Theory0 citations2026-06-19arXiv ->

Conflict-Aware Switching for CBF-CLF-Based Multi-Goal Navigation

Rohan Walia, Kevin Leahy

Quadratic programs (QPs) using Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs) are widely used for safe control in reach-and-avoid navigation. However, the inherently conflicting nature of CBF and CLF constraints can lead to performance degradation, including slowdowns and deadlocks. This issue is exacerbated in multi-goal scenarios, where multiple nominal control objectives must be satisfied under shared safety constraints. Existing approaches for preemptive safety are often computationally expensive or overly conservative, while methods that relax or switch between nominal objectives are not well-suited for sequential goal-to-goal navigation. To address these limitations, we propose a conflict-aware switching strategy that detects high-conflict conditions and switches between available nominal control objectives to reduce constraint conflict. We apply this approach to multi-agent, multi-goal reach-and-avoid scenarios under CBF-CLF-QP control. Compared to a baseline sequential goal traversal strategy, our method reduces both completion time and timeout rates, demonstrating improved performance in satisfying all nominal control objectives while respecting safety constraints.

Robotics0 citations2026-06-17arXiv ->

A Mixed-Reality Testbed for Autonomous Vehicles

H. M. Sabbir Ahmad, Ehsan Sabouni, Emrullah Celik, Zean Wan, Damola Ajeyemi et al.

We propose a mixed-reality, hardware-in-the-loop (HIL) testbed for autonomous vehicles that seamlessly integrates a physical testbed of mobile robots with a high-fidelity simulation environment. The virtual simulation enables the creation of diverse, safety-critical driving scenarios to validate state-of-the-art perception, planning, and control algorithms, while augmenting simulations with physical robots equipped with multimodal sensors in photorealistic virtual environments further facilitating rigorous validation. Our testbed also features vehicular connectivity using wireless communication and can accommodate a large number of agents through the combination of physical robots and virtual simulated agents, supporting research on multi-agent systems including Connected and Autonomous Vehicles (CAVs). Finally, we present a safety-guaranteed framework combining perception, planning and a novel online learning-based controller using Control Barrier Functions (CBFs) for CAVs. Experiments using the proposed framework are used to validate and demonstrate the key functionalities and the overall utility of the testbed to bridge the gap between simulation and real-world hardware deployment.

Robotics0 citations2026-06-15arXiv ->

PolyMerge: Compressing 3D Gaussian Splats with Polytope Coverings for Provably Safe Resource-Constrained Navigation

Jihoon Hong, Chih-Yuan Chiu, Sara Fridovich-Keil, Glen Chou

Obstacle avoidance is essential for safe navigation and motion planning. Recent radiance field reconstruction methods enable object detection and modeling with high fidelity, but remain too memory- and compute-intensive for on-board perception-based path planning. To address these limitations, we propose PolyMerge to convert a large, photorealistic 3D Gaussian Splatting (3DGS) model of a scene into a lightweight representation of convex polytopes whose union provably over-approximates all obstacles in the original 3DGS model. PolyMerge tunes the polytope count to trade off conservativeness and compute cost, and integrates with control barrier functions (CBFs) to plan collision-free paths. We showcase PolyMerge in simulation and hardware experiments on a Crazyflie drone, which uses PolyMerge to compute and follow safe trajectories in real time under severe onboard compute constraints, outperforming baselines in speed while guaranteeing safety. For our code and videos, visit https://athlon76.github.io/PolyMerge-website/.

MPC/Planning0 citations2026-06-13arXiv ->

Robust Conformal CBF and CLF Controllers via Iterative Policy Updates

Omid Mirzaeedodangeh, Eliot Shekhtman, Nikolai Matni, Lars Lindemann

Conformal prediction (CP) has been used to obtain probabilistic bounds on the error between a learned dynamics model and the true but unknown system. Such CP bounds can then be embedded into robust control Lyapunov function (CLF) and control barrier function (CBF) frameworks. However, such an approach does not retain stability/safety guarantees because of the distribution shift between the closed-loop trajectory distribution under the deployed CLF/CBF policy and the trajectory distribution from which the CP bound and its guarantees were derived. To address this issue, we propose an episodic framework that iteratively updates the robust conformal CLF/CBF policy while maintaining stability/safety guarantees across episodes. We achieve this by (1) using adversarially robust conformal prediction, and (2) quantifying a distribution shift budget that allows us to control how much the model error can increase across policy updates. This distribution shift budget is derived via a closed-loop trajectory sensitivity analysis, yielding an implicit and an explicit update rule for the CP bound. We analyze convergence of our algorithm, which we demonstrate on three case studies. To the best of our knowledge, these are the first results that provide stability/safety guarantees for robust conformal CBF/CLF policies.

Robotics0 citations2026-06-12arXiv ->

A Modular Dual-Arm Apple Harvesting Robot with Enhanced Field Performance

Keyi Zhu, Kyle Lammers, Chaaran Arunachalam, Kaixiang Zhang, Renfu Lu et al.

Robotic apple harvesting offers a promising solution to labor shortages in commercial orchards, but low throughput and poor performance in orchard environments hinder its commercial adoption. This paper presents a modular dual-arm apple harvesting robot that uses a vertically stacked arms to enable simultaneous operation in the upper and lower zones of a single tree, simplifying platform positioning from multi-tree lateral repositioning to single-tree stops. Compared to our prior horizontal dual-arm system, the platform integrates 5 advances: (1)a foundation-model-based perception pipeline combining Grounding-DINO and EfficientViT-SAM for robust fruit localization in unstructured outdoor environments; (2)7th-order jerk-bounded trajectory generation paired with a Control Barrier Function safety filter to achieve fast yet safe arm motions; (3)a linear sweep harvesting strategy with a 10cm approach buffer and rotational detachment that improves picking reliability; (4)a temporal-logic-based dual-arm coordination policy with vision-arm async scheduling that maximizes usage of a shared vacuum source; and (5)field validation in 2 commercial orchards covering different apple varieties and tree architectures during the 2025 harvest season. Across the 1738 arm cycles collected in these field trials, the system achieved an 80.0% per-attempt success rate and a mean per-arm cycle time of 7.53s. Fruit damage assessments confirmed that 91.2% of robotically harvested fruit retained the highest USDA grade (Extra Fancy), with bruise rates between 2.4% and 4.9%. With further improvements in the picking cycle time and handling of heavy foliage occlusions, this new modular robot design holds promise for commercial harvesting of apples.

Robotics0 citations2026-06-11arXiv ->

Embedding ISO 10218 Safety Compliance in Robots via Control Barrier Functions for Human-Robot Collaboration

Federico Parma, Cesare Tonola, Nicola Pedrocchi, Manuel Beschi

Human-Robot Collaboration (HRC) requires strict adherence to safety standards, such as ISO 10218, to prevent harmful interactions. Standard Speed and Separation Monitoring (SSM) filters calculate safe robotic speeds based on conservative assumptions, such as constant human velocity, which prevents accurate predictions of minimum separation distances and causes unnecessary operational halts. This paper proposes a Control Barrier Function (CBF) that explicitly incorporates human acceleration data to analytically forward-predict the minimum human-robot separation distance during a worst-case robotic stopping trajectory. To guarantee safety at the control level, this predictive CBF is integrated as an inequality constraint within a Sequential Quadratic Programming (SQP) framework. Specifically, two methods are proposed: Method I, a CBF-constrained PD safety filter; and Method II, a task-scaling SQP controller that enforces a spatial tube constraint. Simulated and real-world experiments on a UR10e robot evaluate the two proposed methods against a standard industrial SSM module baseline. Results demonstrate that Method II dynamically modulates execution speed and confines spatial deviations. Compared to Method I, Method II achieves a 63\% reduction in mean trajectory error and avoids excessive evasive manoeuvres, ensuring high task throughput while complying with ISO 10218 SSM guidelines.

MPC/Planning0 citations2026-06-10arXiv ->

Individual Control Barrier Functions-Guided Diffusion Model for Safe Offline Multi-Agent Reinforcement Learning

Qingyun Guo, Junyi Shi, Jianuo Huang, Tianyu Shi

Offline reinforcement learning allows control policies to be learned directly from data without online interaction, making it suitable for safety-critical tasks. Recent studies have applied diffusion models to offline reinforcement learning to leverage their strong capacity for modeling complex data distributions. However, existing approaches primarily focus on single-agent settings, leaving the safety challenges in multi-agent environments largely unexplored. In this work, we propose a safe offline multi-agent reinforcement learning algorithm that embeds neural individual control barrier functions into the diffusion model to enhance safety during trajectory generation, with control policies recovered through inverse dynamics. We evaluate our algorithm across diverse benchmarks, demonstrating substantial safety improvements while maintaining competitive rewards.

Robotics0 citations2026-06-08arXiv ->

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models

Seongbin Park, Fan Zhang, Baharan Mirzasoleiman, Shahriar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees against collisions with task-irrelevant objects in the scene. Existing safety filters sidestep this problem by querying a vision-language model (VLM) to identify obstacles and their locations. This, however, is too slow to run in the control loop and can only be invoked at episode initialization, leaving the filter unable to track moving obstacles. We discover that a small number of attention heads within a VLA model reliably localize the object the policy intends to approach. These heads can be exploited within a training-free safety framework that obtains the active target from the attention heads at every step, treats the remainder of the scene as obstacles, and feeds these into a Control Barrier Function (CBF) filter. Together with a lightweight real-time object tracker, this allows for collision avoidance for non-static obstacles. We evaluate our framework on SafeLIBERO, which we extend with moving obstacles. On the original static benchmark, our method performs comparably to an oracle that uses privileged simulator state to identify the target, emulating a VLM-based identification step run once at episode initialization. On the dynamic variant, where the oracle's init-time target assignment becomes stale, our method substantially outperforms it by 43%, on average. Our findings suggest that the perceptual signals needed for real-time safety filtering are already present within VLA policies and can be exploited without additional training or heavy auxiliary models.

Robotics0 citations2026-06-08arXiv ->

ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

Fan Zhang, Seongbin Park, Baharan Mirzasoleiman, Shariar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution, yet their generalization capabilities remain fundamentally limited. They3 lack the robustness required to handle perturbations, frequently failing when con-4 fronted with lighting changes, altered camera viewpoints, or small initial-state5 variations. We propose PROBEACT, a training-free runtime intervention frame-6 work that detects and recovers from grasping and placement failures in pre-7 trained VLA policies without modifying their weights or requiring additional8 demonstrations. PROBEACT combines three components: (i) a lightweight multi-9 target hidden-state probe that predicts the 3D positions of task-relevant objects10 from intermediate VLA features, with Hungarian-matched identity tracking for11 multi-object scenes; (ii) an object-agnostic kinematic state machine that detects12 grasp, transport, and placement failures using only gripper-internal signals and13 end-effector kinematics; and (iii) a hierarchical Control Barrier Function (CBF)14 filter that encodes repeated-failure locations as soft safe-set constraints, mini-15 mally correcting VLA actions while preserving baseline behavior. As a plug-and-16 play, training-free intervention loop, PROBEACT is orthogonal to existing train-17 ing pipelines. Evaluated on the LIBERO-plus benchmark, our framework acts as18 a universal safety net, improving the success rate of the OpenVLA-OFT model19 from 69.6% to 74.1%, while demonstrating broad applicability to both base and20 fine-tuned VLA policies.

Robotics0 citations2026-06-08arXiv ->

Safe Polytope-in-Polytope Motion Planning and Control with Control Barrier Functions

Alejandro Gonzalez-Garcia, Dries Dirckx, Jan Swevers, Wilm Decré

Autonomous mobile robots operating in tight environments require motion planning frameworks that account for the physical footprint of the robot. Simplifying the geometry to a point or a circle is conservative and discards information needed to successfully and safely traverse narrow passages. This work proposes a safe local motion planning and control method that guarantees that a polytopic robot footprint stays inside a continuously updated convex free-space region. The containment condition is formulated as a set of discrete-time control barrier function constraints within a model predictive controller. The number of safety constraints depends on the complexity of the local free-space geometry and the robot shape, instead of the number of obstacles. The proposed free-space formulation does not need any obstacle detection or segmentation. A comparative analysis against a polytope-based obstacle avoidance formulation confirms favorable scaling up to a reduction of 91$\times$ in computation time as the number of obstacles increases. The approach is validated in simulation with an autonomous surface vehicle and on hardware with a non-holonomic mobile robot, using both occupancy grids and LiDAR sensing. The experiments demonstrate safe real-time motion planning and control at 10~Hz on an onboard embedded computer, including reactive avoidance of dynamic obstacles.

Robotics0 citations2026-06-01arXiv ->

Embedding Semantic Risk into Distance Fields and CBFs for Online Monocular Safe Control

Dawei Zhang, Nuo Chen, Shuo Liu, Roberto Tron, Zhiwen Fan

We propose an online monocular perception-to-control framework that embeds semantic risk into the distance field used by Control Barrier Function (CBF)-based safe navigation and teleoperation. Many perception-based safety filters assign the same distance-based safety margin to all mapped obstacles or use semantics only as a downstream controller adjustment, rather than encoding semantic risk in the spatial representation. Our framework instead reasons online about obstacle geometry and class-dependent risk by embedding semantic information directly into the Euclidean Signed Distance Field (ESDF). This design encodes semantic risk before control optimization, so high-risk objects exert a larger spatial influence in the safety field while retaining efficient ESDF queries at runtime. Specifically, a foundation-model-based SLAM front end reconstructs dense 3-D geometry from monocular RGB video, while per-frame semantic segmentation provides pixel-level class labels that are fused into the reconstructed geometry. The resulting geometric-semantic representation is then converted into an ESDF, where semantic labels identify safety-relevant regions and impose class-dependent inflation before field computation. The semantic-aware ESDF provides the local distance values and spatial derivatives required by the CBF controller, while class-dependent gains further regulate the controller response. Extensive simulation and hardware experiments demonstrate online operation at 10--20 Hz and semantic-aware safe behavior in both teleoperation and autonomous navigation.

Robotics0 citations2022-09-18arXiv ->

Dynamic Control Barrier Function-based Model Predictive Control to Safety-Critical Obstacle-Avoidance of Mobile Robot

Zhu Jian, Zihong Yan, Xuanang Lei, Zih-Rong Lu, Bin Lan et al.

This paper presents an efficient and safe method to avoid static and dynamic obstacles based on LiDAR. First, point cloud is used to generate a real-time local grid map for obstacle detection. Then, obstacles are clustered by DBSCAN algorithm and enclosed with minimum bounding ellipses (MBEs). In addition, data association is conducted to match each MBE with the obstacle in the current frame. Considering MBE as an observation, Kalman filter (KF) is used to estimate and predict the motion state of the obstacle. In this way, the trajectory of each obstacle in the forward time domain can be parameterized as a set of ellipses. Due to the uncertainty of the MBE, the semi-major and semi-minor axes of the parameterized ellipse are extended to ensure safety. We extend the traditional Control Barrier Function (CBF) and propose Dynamic Control Barrier Function (D-CBF). We combine D-CBF with Model Predictive Control (MPC) to implement safety-critical dynamic obstacle avoidance. Experiments in simulated and real scenarios are conducted to verify the effectiveness of our algorithm. The source code is released for the reference of the community11Code: https://github.com/jianzhuozhuTHU/MPC-D-CBF..

Robotics0 citations2021-09-25arXiv ->

Safety-Critical Control and Planning for Obstacle Avoidance between Polytopes with Control Barrier Functions

A. Thirugnanam, Jun Zeng, K. Sreenath

Obstacle avoidance between polytopes is a chal-lenging topic for optimal control and optimization-based tra-jectory planning problems. Existing work either solves this problem through mixed-integer optimization, relying on simpli-fication of system dynamics, or through model predictive control with dual variables using distance constraints, requiring long horizons for obstacle avoidance. In either case, the solution can only be applied as an offline planning algorithm. In this paper, we exploit the property that a smaller horizon is sufficient for obstacle avoidance by using discrete-time control barrier function (DCBF) constraints and we propose a novel optimization formulation with dual variables based on DCBFs to generate a collision-free dynamically-feasible trajectory. The proposed optimization formulation has lower computational complexity compared to existing work and can be used as a fast online algorithm for control and planning for general nonlinear dynamical systems. We validate our algorithm on different robot shapes using numerical simulations with a kinematic bicycle model, resulting in successful navigation through maze environments with polytopic obstacles.

Robotics0 citations2020-07-22arXiv ->

Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Function

Jun Zeng, Bike Zhang, K. Sreenath

The optimal performance of robotic systems is usually achieved near the limit of state and input bounds. Model predictive control (MPC) is a prevalent strategy to handle these operational constraints, however, safety still remains an open challenge for MPC as it needs to guarantee that the system stays within an invariant set. In order to obtain safe optimal performance in the context of set invariance, we present a safety-critical model predictive control strategy utilizing discrete-time control barrier functions (CBFs), which guarantees system safety and accomplishes optimal performance via model predictive control. We analyze the feasibility and the stability properties of our control design. We verify the properties of our method on a 2D double integrator model for obstacle avoidance. We also validate the algorithm numerically using a competitive car racing example, where the ego car is able to overtake other racing cars.

Systems and Control | 31 papers | 50.0% coverage
MPC/Planning0 citations2026-07-23arXiv ->

Robust Adaptive Backup Control Barrier Functions

Ersin Daş, David E. J. van Wijk, Tamas G. Molnar, Aaron D. Ames, Joel W. Burdick

We propose a notion of robust adaptive backup control barrier functions for nonlinear control affine systems with parametric uncertainty in both the drift dynamics and actuation matrix. Backup control barrier functions guarantee safety by predicting the system's trajectory under a pre-certified safe controller. However, these predictions rely on the model and can be inaccurate when the system contains unknown parameters. To address this issue, we estimate the unknown parameters using element-wise certified adaptive estimators that provide a parameter adaptation law and component-wise estimation error bounds. We compute the backup flow using the estimated model and tighten the safety conditions using these certified bounds. The resulting safety conditions account for the sensitivity of the predicted flow to parameter estimation errors. Moreover, to handle uncertainty in the actuation matrix, we use a duality-based reformulation that enables the use of a computationally efficient quadratic-program-based safety filter. We prove that controllers satisfying the proposed robust adaptive backup control barrier function constraints guarantee safety under parametric uncertainty and input constraints.

MPC/Planning0 citations2026-07-22arXiv ->

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

Robotics0 citations2026-07-22arXiv ->

Safe and Scalable Multi-Drone Payload Transport via CBF-based Reinforcement Learning with Zero-Shot Sim-to-Real Transfer

Jaeyoun Choi, Oswin So, Songyuan Zhang, Cooper Taylor, Chuchu Fan

Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster response. However, the complex coupled dynamics among drones, cables, and payloads pose significant challenges, and existing approaches remain limited in safety and scalability, particularly in dynamic and unstructured environments. In this work, we propose a learning-based framework for safe and scalable multi-drone cooperative payload transport. We introduce a minimal 2D abstraction that preserves the task-relevant drone-payload coupling required for coordination and safety, while remaining computationally efficient for large-scale learning. Using domain randomization over team size and physical parameters, we train a fully distributed policy via Discrete Graph Control Barrier Function Proximal Policy Optimization (DGPPO), enabling robust zero-shot sim-to-real transfer without fine-tuning. Extensive real-world evaluations demonstrate that a single learned policy generalizes across varying team sizes and task scenarios. Furthermore, multi-group hardware experiments show that the same policy can safely operate in dynamic environments, where other drone teams act as moving obstacles. These results indicate that the proposed framework enables efficient, safe, and scalable multi-drone payload transportation with strong generalization to complex real-world conditions.

MPC/Planning0 citations2026-07-21arXiv ->

Pose-Parameterized Motion Planning and CBF-QP Self-Collision Filtering for a Long-Reach Drilling Boom

Mehdi Heydari Shahna, Tuomo Kivelä, Jouni Mattila

Long-reach drilling booms must reach successive poses without self-collision. Moving from operator-supervised control toward autonomy requires collision-aware motion planning and execution. For the Sandvik SB60, this study adapts established methods by integrating pose-parameterized planning with a capsule-based control barrier function quadratic program (CBF-QP) in measured-state inverse kinematics (IK). A fixed task-specific parameter set within each task generates waypoints, detours, timed references, and chained motion without target-specific retuning. The offline detour planner screens candidate waypoints using 23 selected rod-segment-to-body-region distances, whereas the online CBF-QP filters joint velocities using 14 configured capsule-pair constraints from a nine-primitive whole-body capsule model. Evaluation considers two drilling tasks in a manufacturer-developed SB60 Simscape Multibody model: a five-target restricted-orientation tour and a three-target full-pose tour. Across several hundred thousand samples, the method produced zero IK failures, generated several detour waypoints, achieved millimetre-level mean final-position error, and recorded no sampled CBF margins below the reported thresholds.

Theory0 citations2026-07-19arXiv ->

Optimal Safety Control using High-Order Control Barrier Functions

Neng Li, Zuodong Pan, Jiaxing Wang, Weiguo Xia, Wei Ren

This paper investigates the optimal safety control problem of nonlinear control systems by proposing novel high-order control barrier functions (HOCBFs). Different from zeroing HOCBFs, two novel HOCBFs are derived and the safety controllers are designed in an explicit way. Next, we implement vector Lyapunov function approach to propose a novel high-order control Lyapunov function (HOCLF) for the stabilization control problem. The relations between the proposed and existing HOCBFs are discussed. Afterwards, the compatibility of the proposed HOCLF and HOCBF is addressed to guarantee the stabilization and safety control objectives simultaneously, and thus the optimal controller is established. Finally, a numerical example from the navigation problem of quadrotors is presented to illustrate the efficacy of the derived results.

Robotics0 citations2026-07-17arXiv ->

Dynamic Constraint Reconstruction Based Control Barrier Functions for Safety-Critical Control of High-Dimensional Manipulators

Bingsheng Zhang, Shen Wang, Qiang Wang, Muguo Du, Donghai Shi et al.

Control barrier functions (CBFs) provide formal safety guarantees for constrained nonlinear systems, but their effectiveness relies on accurate system dynamics. In high-dimensional manipulators subject to unknown disturbances and model uncertainties, fixed safety constraints constructed from nominal dynamics may become inconsistent with the actual system behavior, leading to safety degradation or excessive conservatism. This paper proposes a dynamic constraint reconstruction based control barrier function (DCR-CBF) framework for safety-critical control of disturbed robotic manipulators. An extended state observer is employed to estimate lumped disturbances online, and the estimated disturbance is incorporated into high-order control barrier functions to reconstruct safety constraints according to the estimated true dynamics. To address estimation inaccuracies, a safety margin is introduced, and a sufficient condition is derived to guarantee forward invariance under bounded estimation errors. Simulation studies on a 4-DOF excavation manipulator demonstrate that the proposed DCR-CBF method achieves zero safety violation under strong unknown disturbances while significantly improving trajectory-tracking performance compared with standard and robust CBF methods.

Robotics0 citations2026-07-14arXiv ->

Autonomous Tracking and Terminal Guidance of Moving Targets for Fixed-Wing UAVs

Wei-Hao Liou, Teng-Hu Cheng

This study introduces a unified control framework for fixed-wing unmanned aerial vehicles (UAVs) fitted with a pan-tilt (PT) camera, intended to perform an end-to-end mission spanning from initial target detection to accurate terminal engagement. The proposed system employs a three-phase strategy: a vision-based target acquisition phase, an NMPC-based tracking phase, and a terminal guidance phase. During tracking, the framework uses an Unscented Kalman Filter (UKF) to fuse YOLO-based visual detections with inertial measurements, enabling robust target state estimation under unknown dynamics. To ensure reliable visual contact, we introduce a constraint-aware Nonlinear Model Predictive Control (NMPC) strategy that incorporates Control Barrier Functions (CBFs) to explicitly prevent UAV self-occlusion -- a common limitation in fixed-wing tracking. Upon satisfying terminal engagement conditions, the system seamlessly transitions control to a quaternion-based Biased Proportional Navigation Guidance (BPNG) law, enforcing precise impact angle constraints. High-fidelity simulations demonstrate that the framework achieves stable, robust tracking and accurate terminal interception while strictly respecting the vehicle's dynamic limits and camera field-of-view constraints.

Robotics0 citations2026-07-12arXiv ->

D-SafeMPC: Diffusion-Driven Safe Model Predictive Control with Discrete-Time Control Barrier Functions

Erdi Sayar, Ersin Daş, Joel W. Burdick, Alois Knoll, Erdal Kayacan

A key limitation on the use of diffusion models in robotic planning is their inability to inherently enforce safety or dynamical constraints, which often results in physically infeasible or unsafe outputs. Hybrid approaches that employ model predictive control (MPC) to address this problem can be unstable, as poor trajectory initializations from the diffusion model prevent the MPC from converging to a safe and feasible solution. To overcome these challenges, we propose D-SafeMPC, which enhances the interaction between diffusion and control. Our method guides the reverse diffusion process with control barrier functions (CBFs) and control Lyapunov functions (CLFs) and employs an iterative-projection scheme where an MPC refines the trajectory at each denoising step. This steers sampling toward safe, goal-directed regions and provides reliable MPC warm starts. In simulations on a Franka manipulator across four scenarios (one static-obstacle and three dynamic-obstacle settings) and in a sim-to-real experiment on a physical Franka robot, D-SafeMPC improves safety, task success rates, and planning efficiency over state-of-the-art baselines. To facilitate reproducibility, our source code and experimental configurations are available in a repository at https://github.com/erdiphd/D-SafeMPC

Learning0 citations2026-07-10arXiv ->

Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation

Alex Zongo, Peng Wei

Learning-based separation assurance for small Unmanned Aircraft Systems (sUAS) achieves near-zero collision rates in simulation, but assumes accurate position and velocity information from Global Navigation Satellite Systems (GNSS). This assumption fails in urban environments, where multipath propagation, signal blockage, and intentional interference degrade navigation integrity. This raises a fundamental architectural question for deploying learned separation policies under GNSS degradation: should runtime safety mechanisms filter the policy's actions or its observations? This work evaluates both approaches for multi-agent sUAS separation under adversarial GNSS degradation. Both architectures first estimate a worst-case traffic state consistent with bounded observation uncertainty, then diverge: action filtering constrains policy outputs via discrete-time control barrier functions evaluated at the worst-case state, while observation filtering presents the worst-case state directly to the policy as corrected input. Experimental results show that action filtering provides negligible safety improvement, while observation filtering reduces near mid-air collisions by 90% and remains robust to the barrier function's tradeoff between separation distance and closing rate. These results suggest that, for policies with learned safety behaviors, preserving the policy's decision authority outperforms overriding its actions with hand-designed constraints.

Robotics0 citations2026-07-10arXiv ->

SEAMLiS: Visibility-Aware Safety for Perception-Limited Multi-Robot Exploration

Taekyung Kim, Rahul H Kumar, Aswin D. Menon, Tzu-Hsiang Lin, Dimitra Panagou

Autonomous exploration in unknown environments is typically driven by informative frontiers, viewpoints, or trajectories, while local safety controllers avoid obstacles represented in the current map. Under finite sensing range and limited field of view, this separation can be unsafe: an exploration stack may plan optimistically through unobserved space and steer the sensor toward information gain rather than along the direction of motion, causing hidden obstacles to be detected too late for bounded-actuation avoidance. This paper presents SEAMLiS (Safe Exploration for Autonomous Multi-Robot Systems Under Limited Sensing), a modular execution-layer safety framework for decentralized multi-robot exploration. SEAMLiS preserves the upstream exploration stack, including the goal allocator and local planner, and enforces safety at the execution layer through perception-aware attitude and positional filters. A gatekeeper-based attitude filter switches between a visibility-promoting yaw policy and a velocity-tracking backup policy to preserve visibility of the critical known-free/unknown boundary with sufficient braking margin. A Control Barrier Function (CBF)-based positional filter then avoids known obstacles, newly detected obstacles, and other robots. We provide sufficient collision-avoidance conditions and validate the framework in randomized simulation, Isaac Sim, and Crazyflie hardware experiments. Results show collision-free exploration across tested single- and multi-robot settings while retaining much of the efficiency of visibility-promoting yaw control.

MPC/Planning0 citations2026-07-02arXiv ->

Reference-Governed Distributed Safe Gradient Flow for Safe Optimal Output Agreement of Multi-Agent Systems

Zhanglin Shangguan, Wei Xiao, Bo Yang, Xinping Guan

This paper studies safe optimal output agreement for nonlinear multi-agent systems with output safety constraints. Existing safe feedback optimization methods often implement gradient-flow dynamics directly through the plant input, which may require high-order control barrier functions (HOCBFs). The resulting derivative-chain design is tuning-sensitive and can introduce additional equilibrium conditions that alter the steady-state optimal solution. We propose a reference-governed two-layer architecture that separates lower-layer output regulation from upper-layer distributed optimization. The upper layer filters the reference gradient flow through first-order control barrier function constraints, which are easier to tune and preserve the steady-state optimality structure of the original agreement problem. The lower layer uses an internal-model-based output regulator with a reference-dependent Lyapunov function, from which dynamic safety margins (DSMs) are constructed to certify transient output safety. We prove forward invariance, optimal-solution preservation under DSM-compatibility conditions, and convergence via a Lyapunov small-gain argument. Simulations validate safe convergence, show advantages over HOCBF-based feedback optimization, and demonstrate adaptive tangential objective shaping for escaping spurious equilibria induced by nonconvex obstacles.

Robotics0 citations2026-07-01arXiv ->

Robust Operational Space Control with Conformal Disturbance Bounds for Safe Redundant Manipulation

Wenhua Liu, Fan Zhang, Qin Lin

Redundant robotic manipulators operating in constrained and human-interactive environments require accurate task-space tracking together with rigorous safety guarantees under dynamic uncertainties. Classical operational space computed torque controller (OSCTC) relies on accurate dynamic models and degrades in the presence of disturbances. In contrast, the data-driven paradigm of residual learning approximates disturbances as functions learned from full-state measurements, which are often noisy in practice, lack rigorous theoretical guarantees, and introduce additional design complexity. This paper proposes a robust OSCTC framework that integrates an extended state observer (ESO) with conformal prediction to combine model-based robustness and data-driven adaptability. The ESO estimates lumped disturbances directly in operational space without requiring full-state measurements as in residual learning, and a robust control barrier function (CBF) is constructed to enforce safety under uncertainty. However, robust CBFs require a known disturbance-variation bound to guarantee absolute safety, which often leads to conservatism in practice. To address this limitation, we further employ a sliding-window conformal prediction mechanism to estimate the bound online in a distribution-free manner, thereby achieving practical probabilistic safety guarantees. Experiments on a 7-DoF Franka Research 3 manipulator demonstrate millimeter-level tracking accuracy and real-time safe control at 1~kHz under various disturbances.

MPC/Planning0 citations2026-06-24arXiv ->

Control Barrier Function only Formation Tracking in Multi-Agent Systems

S. Saharsh, Pushpak Jagtap

This paper presents a real-time control framework for formation tracking of heterogeneous multi-agent systems with non-linear dynamics. The proposed method formulates a single Control Barrier Function-like constraint within a quadratic optimization setting that addresses formation tracking. Relying on the relative information of neighboring agents, the controller is designed to operate without the need for manual parameter tuning or a separate nominal formation controller. The leader-follower framework is validated through simulations of moving formations.

Theory0 citations2026-06-24arXiv ->

Deterministic Non-Smooth Safety via Dual-Algebraic Control Barrier Functions

Mohammadreza Kamaldar

This paper presents a dual-algebraic framework for control barrier functions (CBFs) that guarantees deterministic execution using exclusively elementary arithmetic. We develop this deterministic approach to solve a fundamental bottleneck in safety-critical control: pointwise minima naturally compose intersecting safe sets, but generate non-smooth boundaries where standard Lie derivatives fail. Existing mathematical workarounds inject approximation bias, probabilistic non-determinism, or combinatorial execution delays that strictly impede hard real-time hardware certification. By embedding the system state and vector field into the dual-number ring, our method extracts both the composite barrier value and its exact directional derivative in a single evaluation. The standard floating-point minimum deterministically isolates a single vertex of the Clarke generalized gradient for the quadratic-program solver. We prove this selected vertex constitutes a valid Clarke subgradient and the resulting simultaneous-enforcement safety filter guarantees forward invariance. The arithmetic overhead remains a fixed constant factor, strictly independent of state dimension or constraint count. We extend this framework to arbitrary $\min$/$\max$ Boolean compositions and systems of higher relative degree, validating the computational scaling on three physical examples.

Learning0 citations2026-06-20arXiv ->

Decentralized Geometric Control for Cable-Suspended Payload Transport with Adaptive Mass Estimation

Hadi Hajieghrary, Benedikt Walter, Paul Schmitt, Miguel Hurtado

Cooperative aerial transport requires controllers that respect nonlinear manifold geometry, operate without centralized coordination, and respect operational safety constraints. To address these demands, we present GPAC, a four-layer hierarchical architecture that enables $N$ quadrotors to transport a cable-suspended payload without a central coordinator or by exchanging cable states or adaptive parameters. The key insight is implicit coordination: each quadrotor independently estimates its effective load share from local cable measurements, so combined forces converge to the correct total, even without knowledge of $N$ or the payload mass; the payload position is reconstructed locally from each agent's own cable geometry, and the only inter-agent communication is a low-rate neighbor-position broadcast for collision avoidance. GPAC operates directly on the full nonlinear configuration manifold and integrates geometric position and attitude control, anti-swing regulation, an extended-state observer for wind rejection, concurrent learning-based mass estimation without persistent excitation, and a priority-ordered control barrier function (CBF)-inspired safety filter that reduces operational risk, with input-to-state safety (ISSf) margins that hold exactly under single-constraint activation. A compatibility result shows that the filter's force modifications keep the desired attitude within the almost-global stability region of the $\mathrm{SO}(3)$ attitude controller. Finally, high-fidelity simulation with flexible cables, onboard sensor fusion, and wind turbulence -- with all control and estimation loops closed through the estimator -- yields a mean payload-tracking RMSE of 33.8 cm (2.8\% coefficient of variation over 13 seeds) at a low per-agent computational cost.

Robotics0 citations2026-06-17arXiv ->

A Mixed-Reality Testbed for Autonomous Vehicles

H. M. Sabbir Ahmad, Ehsan Sabouni, Emrullah Celik, Zean Wan, Damola Ajeyemi et al.

We propose a mixed-reality, hardware-in-the-loop (HIL) testbed for autonomous vehicles that seamlessly integrates a physical testbed of mobile robots with a high-fidelity simulation environment. The virtual simulation enables the creation of diverse, safety-critical driving scenarios to validate state-of-the-art perception, planning, and control algorithms, while augmenting simulations with physical robots equipped with multimodal sensors in photorealistic virtual environments further facilitating rigorous validation. Our testbed also features vehicular connectivity using wireless communication and can accommodate a large number of agents through the combination of physical robots and virtual simulated agents, supporting research on multi-agent systems including Connected and Autonomous Vehicles (CAVs). Finally, we present a safety-guaranteed framework combining perception, planning and a novel online learning-based controller using Control Barrier Functions (CBFs) for CAVs. Experiments using the proposed framework are used to validate and demonstrate the key functionalities and the overall utility of the testbed to bridge the gap between simulation and real-world hardware deployment.

MPC/Planning0 citations2026-06-15arXiv ->

An Adjoint-based Neural Regulator for Real-Time Optimal Control with State Constraints

Isaiah A. Agboola, Yuxin Tong, Uduak Inyang-Udoh

This paper introduces a learning-based control framework for real-time constrained optimal control of nonlinear systems with safety guarantees based on the Pontryagin's Minimum Principle. The approach learns a neural co-state (adjoint) policy that encodes optimality through the system Hamiltonian, rather than directly approximating a control law. Feasibility is enforced separately at runtime through an efficient convex projection that incorporates actuator limits and safety constraints expressed as control barrier functions. We refer to this framework as an adjoint-based neural regulator (ANR) as it yields a controller that satisfies constraints while retaining the optimality structure encoded by the learned adjoint. We demonstrate the effectiveness of the proposed framework on nonlinear constrained control tasks using a unicycle model. The ANR achieves performance at par with nonlinear model predictive control at more than two orders of magnitude lower computational cost, while exhibiting near-invariant performance across unseen scenarios, thus, significantly outperforming reinforcement learning methods in out-of-training-distribution regimes.

Theory0 citations2026-06-14arXiv ->

Stability Analysis in Multi-Constraint Safety Filters for Linear Systems

Shima Sadat Mousavi, Pol Mestres, Aaron D. Ames

Multi-constraint safety filters based on control barrier functions for linear systems with affine state constraints yield continuous piecewise-affine closed-loop dynamics and may introduce boundary equilibria and unstable active-set modes. Although they guarantee forward invariance, they can change nominal stability, and it remains unclear when unstable modes cause divergence versus bounded, convergent behavior. This paper develops a geometric framework to separate these cases: leveraging explicit active-set realizations, we show that equilibria associated with nonempty active sets lie on the corresponding constraint faces and that any unstable directions are tangent to those faces due to exponential enforcement of the active constraints. We characterize mode stability via a minimum-phase test, certify divergence under fixed active sets using recession cones, and derive tractable linear-matrix-inequality conditions for global exponential stability or boundedness using Lyapunov and LaSalle arguments.

MPC/Planning0 citations2026-06-13arXiv ->

Robust Conformal CBF and CLF Controllers via Iterative Policy Updates

Omid Mirzaeedodangeh, Eliot Shekhtman, Nikolai Matni, Lars Lindemann

Conformal prediction (CP) has been used to obtain probabilistic bounds on the error between a learned dynamics model and the true but unknown system. Such CP bounds can then be embedded into robust control Lyapunov function (CLF) and control barrier function (CBF) frameworks. However, such an approach does not retain stability/safety guarantees because of the distribution shift between the closed-loop trajectory distribution under the deployed CLF/CBF policy and the trajectory distribution from which the CP bound and its guarantees were derived. To address this issue, we propose an episodic framework that iteratively updates the robust conformal CLF/CBF policy while maintaining stability/safety guarantees across episodes. We achieve this by (1) using adversarially robust conformal prediction, and (2) quantifying a distribution shift budget that allows us to control how much the model error can increase across policy updates. This distribution shift budget is derived via a closed-loop trajectory sensitivity analysis, yielding an implicit and an explicit update rule for the CP bound. We analyze convergence of our algorithm, which we demonstrate on three case studies. To the best of our knowledge, these are the first results that provide stability/safety guarantees for robust conformal CBF/CLF policies.

MPC/Planning0 citations2026-06-10arXiv ->

Individual Control Barrier Functions-Guided Diffusion Model for Safe Offline Multi-Agent Reinforcement Learning

Qingyun Guo, Junyi Shi, Jianuo Huang, Tianyu Shi

Offline reinforcement learning allows control policies to be learned directly from data without online interaction, making it suitable for safety-critical tasks. Recent studies have applied diffusion models to offline reinforcement learning to leverage their strong capacity for modeling complex data distributions. However, existing approaches primarily focus on single-agent settings, leaving the safety challenges in multi-agent environments largely unexplored. In this work, we propose a safe offline multi-agent reinforcement learning algorithm that embeds neural individual control barrier functions into the diffusion model to enhance safety during trajectory generation, with control policies recovered through inverse dynamics. We evaluate our algorithm across diverse benchmarks, demonstrating substantial safety improvements while maintaining competitive rewards.

Other0 citations2026-06-10arXiv ->

CBF-based Driving Assistance for Traffic Flow Stabilization

Hayate Irie, Masaki Inoue, Banri Okita, Akira Yamaguchi, Tomohiro Taki et al.

This manuscript addresses a hierarchical control system designed to suppress traffic congestion. The lower-layered controllers, implemented in each controlled vehicle, monitor microscopic vehicle behaviors and assist human drivers to ensure sufficient spacing for following vehicles. This spacing logic is designed based on the Control Barrier Function. Meanwhile, the upper-layered controller monitors the macroscopic traffic flow and activates the necessary lower-layered controllers, using a data-driven approach for the activation logic design. Furthermore, the effectiveness of the proposed control system is evaluated in a traffic flow simulation environment constructed using real-world traffic data.

MPC/Planning0 citations2026-06-06arXiv ->

Exactness Certificates for Closed-Form CBF Safety-Filter Projections

Ankit Goel

For control-affine systems, standard and high-order control barrier function conditions are affine in the control input and are commonly enforced through quadratic-program-based safety filters. Although convex, these optimization problems may be undesirable in embedded, high-rate, or resource-limited implementations. This letter characterizes when the corresponding Euclidean projection can be recovered from the affine inequalities violated by a nominal control input. Given a nominal input, we form the violated set and compute the minimum-norm correction that enforces the violated inequalities with equality. This violated-set correction is closed form, but it need not equal the exact Euclidean projection onto the full feasible set. The main result gives a necessary and sufficient exactness certificate based on primal and dual feasibility, followed by structural sufficient conditions involving interactions among affine-inequality normals. An online certification algorithm is then presented to determine when the closed-form update is exact. When the certificate fails, a finite active-set search can be used to recover the exact projection. Numerical simulations illustrate that the violated-set correction can remain feasible while failing to be the exact projection due to dual infeasibility, and demonstrate computational speedup relative to a standard CBF-QP solver.

MPC/Planning0 citations2026-06-06arXiv ->

A Barrier-Modulated Architecture for Safe Affine Formation Control in Second-Order Multi-Agent Systems

Ashik Abrar Naeem, Mohammad Ariful Haque

Affine formation control offers immense flexibility for coordinating multi-agent maneuvers, but guaranteeing the safety of agents under parametric uncertainties remains an open challenge. This paper proposes a novel safe affine formation control framework for second-order multi-agent systems by integrating Higher-Order Control Barrier Functions (HOCBFs) with Adaptive Dynamic Programming (ADP). We introduce a barrier-modulated control architecture that smoothly attenuates the nominal formation tracking objective when agents approach safety boundaries, preventing conflicting control inputs. Within this architecture, two distinct safety controllers are developed: (1) an analytical barrier-gradient repulsive controller that provides a computationally efficient, rigorous mathematical baseline, and (2) a data-driven optimal safety controller. The data-driven approach utilizes an actor-critic neural network to solve the Hamilton-Jacobi-Bellman (HJB) equation online, enabling optimal collision avoidance even in the presence of unknown system parameters. Using Nagumo's theorem and Lyapunov stability analysis, we formally prove that both controllers guarantee the forward invariance of the safe set ensuring absolute collision avoidance while maintaining Uniformly Ultimately Bounded (UUB) formation tracking errors. Finally, simulations validate the theoretical findings and demonstrate the robustness of the proposed controllers in dynamic obstacle avoidance scenarios.

Robotics0 citations2026-06-03arXiv ->

A model-free approach to control barrier functions for higher-order systems

Lukas Lanza, Johannes Köhler, Dario Dennstädt, Thomas Berger, Karl Worthmann

Control barrier functions (CBFs) are a widely applied modular tool to ensure safe operation of nonlinear dynamical control systems. However, for their construction accurate knowledge of the system dynamics is typically needed. This requirement was recently alleviated for relative-degree-one systems using techniques from prescribed performance control (PPC) or funnel control (FC). This article extends the model-free CBF design to nonlinear systems of arbitrary relative degree. Moreover, we show with a simple example that a straightforward extension of existing results for relative-degree-one systems fails. Instead, we utilize novel techniques from funnel control to characterize a subset of the controls satisfying a CBF condition without requiring a dynamic model or state measurement. Finally, we demonstrate the applicability of our results on a seven degrees of freedom robotic manipulator with relative degree two.

MPC/Planning0 citations2026-06-01arXiv ->

Power System CBFs

Abdallah Alalem B. Albustami, Ahmad F. Taha, Taylor T. Johnson

Control barrier functions (CBFs) have become a standard tool in safety critical-control systems. CBFs convert state constraints into real time control conditions that certify forward invariance (meaning that once the system starts in a safe region, it remains there for all future times) and minimally modify a nominal controller only when safety is at risk. In power systems, CBF based methods have been proposed for frequency and voltage safety, but they largely remain disconnected from three key features that are central to power system operation: differential algebraic equation (DAE) models that capture network power flow constraints, safety specifications involving algebraic variables such as bus voltages, and formal verification of the resulting closed loop system. This paper closes this gap by developing a CBF framework for power system DAE models that supports safety constraints on both dynamic and algebraic variables. The framework provides real time safety filtering through an optimization layer that wraps around an existing controller and minimally modifies its command to enforce safety. In addition, it provides formal verification (i.e., a mathematical guarantee that all admissible trajectories satisfy the prescribed safety constraints) through an offline reachability based certificate of safe operation. The result is a unified filter and verify methodology for enforcing and certifying frequency and voltage safety in power systems while preserving the DAE structure of the underlying model.

Robotics0 citations2021-09-25arXiv ->

Safety-Critical Control and Planning for Obstacle Avoidance between Polytopes with Control Barrier Functions

A. Thirugnanam, Jun Zeng, K. Sreenath

Obstacle avoidance between polytopes is a chal-lenging topic for optimal control and optimization-based tra-jectory planning problems. Existing work either solves this problem through mixed-integer optimization, relying on simpli-fication of system dynamics, or through model predictive control with dual variables using distance constraints, requiring long horizons for obstacle avoidance. In either case, the solution can only be applied as an offline planning algorithm. In this paper, we exploit the property that a smaller horizon is sufficient for obstacle avoidance by using discrete-time control barrier function (DCBF) constraints and we propose a novel optimization formulation with dual variables based on DCBFs to generate a collision-free dynamically-feasible trajectory. The proposed optimization formulation has lower computational complexity compared to existing work and can be used as a fast online algorithm for control and planning for general nonlinear dynamical systems. We validate our algorithm on different robot shapes using numerical simulations with a kinematic bicycle model, resulting in successful navigation through maze environments with polytopic obstacles.

MPC/Planning0 citations2021-04-06arXiv ->

Robust Control Barrier–Value Functions for Safety-Critical Control

Jason J. Choi, Donggun Lee, K. Sreenath, C. Tomlin, Sylvia L. Herbert

This paper works towards unifying two popular approaches in the safety control community: Hamilton-Jacobi (HJ) reachability and Control Barrier Functions (CBFs). HJ Reachability has methods for direct construction of value functions that provide safety guarantees and safe controllers, however the online implementation can be overly conservative and/or rely on chattering bang-bang control. The CBF community has methods for safe-guarding controllers in the form of point-wise optimization using quadratic programs (CBF-QP), where the CBF-based safety certificate is used as a constraint. However, finding a valid CBF for a general dynamical system is challenging. This paper unifies these two methods by introducing a new reachability formulation inspired by the structure of CBFs to construct a Control Barrier-Value Function (CBVF). We verify that CBVF is a viscosity solution to a novel Hamilton-Jacobi-Isaacs Variational Inequality and preserves the same safety guarantee as the original reachability formulation. Finally, inspired by the CBF-QP, we propose a QP-based online control synthesis for systems affine in control and disturbance, whose solution is always the CBVF’s optimal control signal robust to bounded disturbance. We demonstrate the benefit of using the CBVFs for double-integrator and Dubins car systems by comparing it to previous methods.

Robotics0 citations2020-07-22arXiv ->

Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Function

Jun Zeng, Bike Zhang, K. Sreenath

The optimal performance of robotic systems is usually achieved near the limit of state and input bounds. Model predictive control (MPC) is a prevalent strategy to handle these operational constraints, however, safety still remains an open challenge for MPC as it needs to guarantee that the system stays within an invariant set. In order to obtain safe optimal performance in the context of set invariance, we present a safety-critical model predictive control strategy utilizing discrete-time control barrier functions (CBFs), which guarantees system safety and accomplishes optimal performance via model predictive control. We analyze the feasibility and the stability properties of our control design. We verify the properties of our method on a 2D double integrator model for obstacle avoidance. We also validate the algorithm numerically using a competitive car racing example, where the ego car is able to overtake other racing cars.

MPC/Planning0 citations2020-03-17arXiv ->

Control Barrier Function-Based Quadratic Programs Introduce Undesirable Asymptotically Stable Equilibria

Matheus F. Reis, Antonio Pedro Aguiar, P. Tabuada

Control Lyapunov functions (CLFs) and control barrier functions (CBFs) have been used to develop provably safe controllers by means of quadratic programs (QPs), guaranteeing safety in the form of trajectory invariance with respect to a given set. In this letter, we show that this framework can introduce equilibrium points (particularly at the boundary of the safe set) other than the minimum of the Lyapunov function into the closed-loop system. We derive explicit conditions under which these undesired equilibria (which can even appear in the simple case of linear systems with just one convex unsafe set) are asymptotically stable. To address this issue, we propose an extension to the QP-based controller unifying CLFs and CBFs such that the resulting system trajectories avoid the undesirable equilibria problem on the boundary of the safe set. The solution is illustrated in the design of a collision-free controller.

MPC/Planning0 citations2019-09-10arXiv ->

A Barrier Function Approach to Finite-Time Stochastic System Verification and Control

Cesar Santoyo, Maxence Dutreix, Samuel D. Coogan

This paper studies the problem of enforcing safety of a stochastic dynamical system over a finite-time horizon. We use stochastic control barrier functions as a means to quantify the probability that a system exits a given safe region of the state space in finite time. A barrier certificate condition that bounds the expected value of the barrier function over the time horizon is recast as a sum-of-squares optimization problem for efficient numerical computation. Unlike prior works, the proposed certificate condition includes a state-dependent upper bound on the evolution of the expectation. We present formulations for both continuous-time and discrete-time systems. Moreover, for systems for which the drift dynamics are affine-in-control, we propose a method for synthesizing polynomial state feedback controllers that achieve a specified probability of safety. Several case studies are presented which benchmark and illustrate the performance of our verification and control method in the continuous-time and discrete-time domains.

MPC/Planning2673 citations2016-09-21arXiv ->

Control Barrier Function Based Quadratic Programs for Safety Critical Systems

A. Ames, Xiangru Xu, J. Grizzle, P. Tabuada

Safety critical systems involve the tight coupling between potentially conflicting control objectives and safety constraints. As a means of creating a formal framework for controlling systems of this form, and with a view toward automotive applications, this paper develops a methodology that allows safety conditions—expressed as control barrier functions—to be unified with performance objectives—expressed as control Lyapunov functions—in the context of real-time optimization-based controllers. Safety conditions are specified in terms of forward invariance of a set, and are verified via two novel generalizations of barrier functions; in each case, the existence of a barrier function satisfying Lyapunov-like conditions implies forward invariance of the set, and the relationship between these two classes of barrier functions is characterized. In addition, each of these formulations yields a notion of control barrier function (CBF), providing inequality constraints in the control input that, when satisfied, again imply forward invariance of the set. Through these constructions, CBFs can naturally be unified with control Lyapunov functions (CLFs) in the context of a quadratic program (QP); this allows for the achievement of control objectives (represented by CLFs) subject to conditions on the admissible states of the system (represented by CBFs). The mediation of safety and performance through a QP is demonstrated on adaptive cruise control and lane keeping, two automotive control problems that present both safety and performance considerations coupled with actuator bounds.

Optimization and Control | 11 papers | 17.7% coverage
MPC/Planning0 citations2026-07-22arXiv ->

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

Robotics0 citations2026-07-18arXiv ->

ADMM-Based Safety-Critical Distributed NMPC for Cooperative Transportation by Quadrupedal Robots

Ruturaj S. Sambhus, Kapi Ketan Mehta, Yicheng Zeng, Kaveh Akbari Hamed

This paper presents a safety-critical distributed nonlinear model predictive control (DNMPC) framework for cooperative payload transportation by teams of quadrupedal robots. The proposed approach models the robotic team and the shared payload as a dynamically coupled networked system with rigid holonomic coupling constraints arising from cooperative transportation. To enable distributed real-time optimization, the centralized finite-horizon optimal control problem is decomposed into parallel local NMPC subproblems coordinated through the alternating direction method of multipliers (ADMM). The resulting distributed framework enforces consensus over both payload-state and interaction-wrench trajectories while explicitly incorporating acceleration-level holonomic coupling constraints within the distributed predictive control formulation. Safety-critical obstacle avoidance constraints for both the robotic agents and payload are enforced using higher-order control barrier functions (HOCBFs). The framework is validated through numerical simulations with teams of two, three, and four quadrupedal robots transporting shared payloads in cluttered environments. Real-time experiments on two- and three-robot teams demonstrate safe and robust transportation under payload uncertainty and external disturbances. Compared with centralized NMPC, the proposed framework achieves up to 23% reduction in average NLP solve time while maintaining comparable closed-loop performance. Ablation studies further demonstrate robustness to communication delays and show that explicit payload-state consensus and holonomic constraints substantially improve payload tracking and distributed coordination over existing wrench-only consensus formulations.

Theory0 citations2026-06-24arXiv ->

Deterministic Non-Smooth Safety via Dual-Algebraic Control Barrier Functions

Mohammadreza Kamaldar

This paper presents a dual-algebraic framework for control barrier functions (CBFs) that guarantees deterministic execution using exclusively elementary arithmetic. We develop this deterministic approach to solve a fundamental bottleneck in safety-critical control: pointwise minima naturally compose intersecting safe sets, but generate non-smooth boundaries where standard Lie derivatives fail. Existing mathematical workarounds inject approximation bias, probabilistic non-determinism, or combinatorial execution delays that strictly impede hard real-time hardware certification. By embedding the system state and vector field into the dual-number ring, our method extracts both the composite barrier value and its exact directional derivative in a single evaluation. The standard floating-point minimum deterministically isolates a single vertex of the Clarke generalized gradient for the quadratic-program solver. We prove this selected vertex constitutes a valid Clarke subgradient and the resulting simultaneous-enforcement safety filter guarantees forward invariance. The arithmetic overhead remains a fixed constant factor, strictly independent of state dimension or constraint count. We extend this framework to arbitrary $\min$/$\max$ Boolean compositions and systems of higher relative degree, validating the computational scaling on three physical examples.

Theory0 citations2026-06-14arXiv ->

Stability Analysis in Multi-Constraint Safety Filters for Linear Systems

Shima Sadat Mousavi, Pol Mestres, Aaron D. Ames

Multi-constraint safety filters based on control barrier functions for linear systems with affine state constraints yield continuous piecewise-affine closed-loop dynamics and may introduce boundary equilibria and unstable active-set modes. Although they guarantee forward invariance, they can change nominal stability, and it remains unclear when unstable modes cause divergence versus bounded, convergent behavior. This paper develops a geometric framework to separate these cases: leveraging explicit active-set realizations, we show that equilibria associated with nonempty active sets lie on the corresponding constraint faces and that any unstable directions are tangent to those faces due to exponential enforcement of the active constraints. We characterize mode stability via a minimum-phase test, certify divergence under fixed active sets using recession cones, and derive tractable linear-matrix-inequality conditions for global exponential stability or boundedness using Lyapunov and LaSalle arguments.

MPC/Planning0 citations2026-06-13arXiv ->

Robust Conformal CBF and CLF Controllers via Iterative Policy Updates

Omid Mirzaeedodangeh, Eliot Shekhtman, Nikolai Matni, Lars Lindemann

Conformal prediction (CP) has been used to obtain probabilistic bounds on the error between a learned dynamics model and the true but unknown system. Such CP bounds can then be embedded into robust control Lyapunov function (CLF) and control barrier function (CBF) frameworks. However, such an approach does not retain stability/safety guarantees because of the distribution shift between the closed-loop trajectory distribution under the deployed CLF/CBF policy and the trajectory distribution from which the CP bound and its guarantees were derived. To address this issue, we propose an episodic framework that iteratively updates the robust conformal CLF/CBF policy while maintaining stability/safety guarantees across episodes. We achieve this by (1) using adversarially robust conformal prediction, and (2) quantifying a distribution shift budget that allows us to control how much the model error can increase across policy updates. This distribution shift budget is derived via a closed-loop trajectory sensitivity analysis, yielding an implicit and an explicit update rule for the CP bound. We analyze convergence of our algorithm, which we demonstrate on three case studies. To the best of our knowledge, these are the first results that provide stability/safety guarantees for robust conformal CBF/CLF policies.

MPC/Planning0 citations2026-06-06arXiv ->

Exactness Certificates for Closed-Form CBF Safety-Filter Projections

Ankit Goel

For control-affine systems, standard and high-order control barrier function conditions are affine in the control input and are commonly enforced through quadratic-program-based safety filters. Although convex, these optimization problems may be undesirable in embedded, high-rate, or resource-limited implementations. This letter characterizes when the corresponding Euclidean projection can be recovered from the affine inequalities violated by a nominal control input. Given a nominal input, we form the violated set and compute the minimum-norm correction that enforces the violated inequalities with equality. This violated-set correction is closed form, but it need not equal the exact Euclidean projection onto the full feasible set. The main result gives a necessary and sufficient exactness certificate based on primal and dual feasibility, followed by structural sufficient conditions involving interactions among affine-inequality normals. An online certification algorithm is then presented to determine when the closed-form update is exact. When the certificate fails, a finite active-set search can be used to recover the exact projection. Numerical simulations illustrate that the violated-set correction can remain feasible while failing to be the exact projection due to dual infeasibility, and demonstrate computational speedup relative to a standard CBF-QP solver.

Robotics0 citations2026-06-05arXiv ->

Verification Framework for the Union of Control Barrier Functions

Chuanrui Jiang, Andrew Clark

Control Barrier Functions (CBFs) have been proposed to ensure safety of autonomous systems. This paper considers control policies that switch between CBF constraints. Under this approach, we represent a complex non-convex safe region as a union of sets that are computationally tractable to verify. We denote this framework as union-CBFs and make the following contributions. First, considering switching CBF-QP controllers, we propose a sufficient condition that ensures (i) the system undergoes a finite number of switches in any finite time interval and ensures (ii) the forward invariance of the closed-loop system in between switches. Second, we consider two types of switching strategies and propose union-CBFs conditions for each strategy to satisfy (i) and (ii). Third, we formulate Sum-of-Squares (SOS) algorithms to verify the conditions. The experiments show that our union-CBFs framework results in a larger safe region compared to high-degree polynomial CBFs. We also show the efficiency of the verification algorithms using a polynomial system model.

Robotics0 citations2026-06-03arXiv ->

A model-free approach to control barrier functions for higher-order systems

Lukas Lanza, Johannes Köhler, Dario Dennstädt, Thomas Berger, Karl Worthmann

Control barrier functions (CBFs) are a widely applied modular tool to ensure safe operation of nonlinear dynamical control systems. However, for their construction accurate knowledge of the system dynamics is typically needed. This requirement was recently alleviated for relative-degree-one systems using techniques from prescribed performance control (PPC) or funnel control (FC). This article extends the model-free CBF design to nonlinear systems of arbitrary relative degree. Moreover, we show with a simple example that a straightforward extension of existing results for relative-degree-one systems fails. Instead, we utilize novel techniques from funnel control to characterize a subset of the controls satisfying a CBF condition without requiring a dynamic model or state measurement. Finally, we demonstrate the applicability of our results on a seven degrees of freedom robotic manipulator with relative degree two.

Robotics0 citations2021-09-25arXiv ->

Safety-Critical Control and Planning for Obstacle Avoidance between Polytopes with Control Barrier Functions

A. Thirugnanam, Jun Zeng, K. Sreenath

Obstacle avoidance between polytopes is a chal-lenging topic for optimal control and optimization-based tra-jectory planning problems. Existing work either solves this problem through mixed-integer optimization, relying on simpli-fication of system dynamics, or through model predictive control with dual variables using distance constraints, requiring long horizons for obstacle avoidance. In either case, the solution can only be applied as an offline planning algorithm. In this paper, we exploit the property that a smaller horizon is sufficient for obstacle avoidance by using discrete-time control barrier function (DCBF) constraints and we propose a novel optimization formulation with dual variables based on DCBFs to generate a collision-free dynamically-feasible trajectory. The proposed optimization formulation has lower computational complexity compared to existing work and can be used as a fast online algorithm for control and planning for general nonlinear dynamical systems. We validate our algorithm on different robot shapes using numerical simulations with a kinematic bicycle model, resulting in successful navigation through maze environments with polytopic obstacles.

MPC/Planning0 citations2020-03-17arXiv ->

Control Barrier Function-Based Quadratic Programs Introduce Undesirable Asymptotically Stable Equilibria

Matheus F. Reis, Antonio Pedro Aguiar, P. Tabuada

Control Lyapunov functions (CLFs) and control barrier functions (CBFs) have been used to develop provably safe controllers by means of quadratic programs (QPs), guaranteeing safety in the form of trajectory invariance with respect to a given set. In this letter, we show that this framework can introduce equilibrium points (particularly at the boundary of the safe set) other than the minimum of the Lyapunov function into the closed-loop system. We derive explicit conditions under which these undesired equilibria (which can even appear in the simple case of linear systems with just one convex unsafe set) are asymptotically stable. To address this issue, we propose an extension to the QP-based controller unifying CLFs and CBFs such that the resulting system trajectories avoid the undesirable equilibria problem on the boundary of the safe set. The solution is illustrated in the design of a collision-free controller.

MPC/Planning2673 citations2016-09-21arXiv ->

Control Barrier Function Based Quadratic Programs for Safety Critical Systems

A. Ames, Xiangru Xu, J. Grizzle, P. Tabuada

Safety critical systems involve the tight coupling between potentially conflicting control objectives and safety constraints. As a means of creating a formal framework for controlling systems of this form, and with a view toward automotive applications, this paper develops a methodology that allows safety conditions—expressed as control barrier functions—to be unified with performance objectives—expressed as control Lyapunov functions—in the context of real-time optimization-based controllers. Safety conditions are specified in terms of forward invariance of a set, and are verified via two novel generalizations of barrier functions; in each case, the existence of a barrier function satisfying Lyapunov-like conditions implies forward invariance of the set, and the relationship between these two classes of barrier functions is characterized. In addition, each of these formulations yields a notion of control barrier function (CBF), providing inequality constraints in the control input that, when satisfied, again imply forward invariance of the set. Through these constructions, CBFs can naturally be unified with control Lyapunov functions (CLFs) in the context of a quadratic program (QP); this allows for the achievement of control objectives (represented by CLFs) subject to conditions on the admissible states of the system (represented by CBFs). The mediation of safety and performance through a QP is demonstrated on adaptive cruise control and lane keeping, two automotive control problems that present both safety and performance considerations coupled with actuator bounds.

Machine Learning | 5 papers | 8.1% coverage
MPC/Planning0 citations2026-07-22arXiv ->

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher et al.

We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs into end-to-end policy training requires embedding a quadratic-program-based safety filter as an optimization layer, but computational and differentiation bottlenecks have largely restricted prior approaches to low-dimensional systems, typically with at most 16 state dimensions. We address this limitation by combining operator splitting with the recently developed Jacobian-Free Backpropagation (JFB) method to enable scalable end-to-end training while preserving hard safety guarantees through the CBF safety filter. We justify this training methodology theoretically using nonsmooth analysis techniques and demonstrate its effectiveness on high-dimensional multi-agent nonlinear control problems with state and control dimensions up to 1200 and 400, respectively.

Learning0 citations2026-07-10arXiv ->

Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation

Alex Zongo, Peng Wei

Learning-based separation assurance for small Unmanned Aircraft Systems (sUAS) achieves near-zero collision rates in simulation, but assumes accurate position and velocity information from Global Navigation Satellite Systems (GNSS). This assumption fails in urban environments, where multipath propagation, signal blockage, and intentional interference degrade navigation integrity. This raises a fundamental architectural question for deploying learned separation policies under GNSS degradation: should runtime safety mechanisms filter the policy's actions or its observations? This work evaluates both approaches for multi-agent sUAS separation under adversarial GNSS degradation. Both architectures first estimate a worst-case traffic state consistent with bounded observation uncertainty, then diverge: action filtering constrains policy outputs via discrete-time control barrier functions evaluated at the worst-case state, while observation filtering presents the worst-case state directly to the policy as corrected input. Experimental results show that action filtering provides negligible safety improvement, while observation filtering reduces near mid-air collisions by 90% and remains robust to the barrier function's tradeoff between separation distance and closing rate. These results suggest that, for policies with learned safety behaviors, preserving the policy's decision authority outperforms overriding its actions with hand-designed constraints.

Robotics0 citations2026-06-16arXiv ->

Memory-Efficient Meta-Reinforcement Learning for Adaptive Safety-Critical Control in Adversarial Spacecraft Proximity Operations

Alejandro Posadas-Nava, Richard Linares, Minduli Wijayatunga

Autonomous spacecraft rendezvous and proximity operations (RPO) require controllers that guarantee safety under thrust constraints while minimizing fuel expenditure. Input-constrained control barrier functions (ICCBFs) provide a control method for nonlinear systems with actuation constraints that construct a forward-invariant safe set. Previous work has shown that learning class-$\mathcal{K}$ functions defining the ICCBF recursion via meta reinforcement learning (meta-RL) yields a robust, non-greedy approach to safety-critical control in RPO. This paper extends that framework further by investigating the performance of three recurrent network architectures (Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Selective State Space Model (Mamba)) and two training algorithms (Proximal Policy Optimization (PPO) and Soft Actor Critic (SAC)) to identify the best setup for tuning ICCBF class-K functions via meta-RL. In addition to cooperative test cases, performance is evaluated in the presence of adversarial behavior where the target spacecraft behaves in a way that worsens the safety of the chaser spacecraft. Results indicate that state space models such as Mamba when used with PPO achieve superior task completion, safety, and fuel-savings compared to other architectures, across all cooperative and uncooperative scenarios tested.

MPC/Planning0 citations2026-06-10arXiv ->

Individual Control Barrier Functions-Guided Diffusion Model for Safe Offline Multi-Agent Reinforcement Learning

Qingyun Guo, Junyi Shi, Jianuo Huang, Tianyu Shi

Offline reinforcement learning allows control policies to be learned directly from data without online interaction, making it suitable for safety-critical tasks. Recent studies have applied diffusion models to offline reinforcement learning to leverage their strong capacity for modeling complex data distributions. However, existing approaches primarily focus on single-agent settings, leaving the safety challenges in multi-agent environments largely unexplored. In this work, we propose a safe offline multi-agent reinforcement learning algorithm that embeds neural individual control barrier functions into the diffusion model to enhance safety during trajectory generation, with control policies recovered through inverse dynamics. We evaluate our algorithm across diverse benchmarks, demonstrating substantial safety improvements while maintaining competitive rewards.

Robotics0 citations2026-06-08arXiv ->

Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models

Seongbin Park, Fan Zhang, Baharan Mirzasoleiman, Shahriar Talebi, Nader Sehatbakhsh

Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees against collisions with task-irrelevant objects in the scene. Existing safety filters sidestep this problem by querying a vision-language model (VLM) to identify obstacles and their locations. This, however, is too slow to run in the control loop and can only be invoked at episode initialization, leaving the filter unable to track moving obstacles. We discover that a small number of attention heads within a VLA model reliably localize the object the policy intends to approach. These heads can be exploited within a training-free safety framework that obtains the active target from the attention heads at every step, treats the remainder of the scene as obstacles, and feeds these into a Control Barrier Function (CBF) filter. Together with a lightweight real-time object tracker, this allows for collision avoidance for non-static obstacles. We evaluate our framework on SafeLIBERO, which we extend with moving obstacles. On the original static benchmark, our method performs comparably to an oracle that uses privileged simulator state to identify the target, emulating a VLM-based identification step run once at episode initialization. On the dynamic variant, where the oracle's init-time target assignment becomes stale, our method substantially outperforms it by 43%, on average. Our findings suggest that the perceptual signals needed for real-time safety filtering are already present within VLA policies and can be exploited without additional training or heavy auxiliary models.

cs.MA | 3 papers | 4.8% coverage
Robotics0 citations2026-07-22arXiv ->

Safe and Scalable Multi-Drone Payload Transport via CBF-based Reinforcement Learning with Zero-Shot Sim-to-Real Transfer

Jaeyoun Choi, Oswin So, Songyuan Zhang, Cooper Taylor, Chuchu Fan

Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster response. However, the complex coupled dynamics among drones, cables, and payloads pose significant challenges, and existing approaches remain limited in safety and scalability, particularly in dynamic and unstructured environments. In this work, we propose a learning-based framework for safe and scalable multi-drone cooperative payload transport. We introduce a minimal 2D abstraction that preserves the task-relevant drone-payload coupling required for coordination and safety, while remaining computationally efficient for large-scale learning. Using domain randomization over team size and physical parameters, we train a fully distributed policy via Discrete Graph Control Barrier Function Proximal Policy Optimization (DGPPO), enabling robust zero-shot sim-to-real transfer without fine-tuning. Extensive real-world evaluations demonstrate that a single learned policy generalizes across varying team sizes and task scenarios. Furthermore, multi-group hardware experiments show that the same policy can safely operate in dynamic environments, where other drone teams act as moving obstacles. These results indicate that the proposed framework enables efficient, safe, and scalable multi-drone payload transportation with strong generalization to complex real-world conditions.

Learning0 citations2026-07-10arXiv ->

Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation

Alex Zongo, Peng Wei

Learning-based separation assurance for small Unmanned Aircraft Systems (sUAS) achieves near-zero collision rates in simulation, but assumes accurate position and velocity information from Global Navigation Satellite Systems (GNSS). This assumption fails in urban environments, where multipath propagation, signal blockage, and intentional interference degrade navigation integrity. This raises a fundamental architectural question for deploying learned separation policies under GNSS degradation: should runtime safety mechanisms filter the policy's actions or its observations? This work evaluates both approaches for multi-agent sUAS separation under adversarial GNSS degradation. Both architectures first estimate a worst-case traffic state consistent with bounded observation uncertainty, then diverge: action filtering constrains policy outputs via discrete-time control barrier functions evaluated at the worst-case state, while observation filtering presents the worst-case state directly to the policy as corrected input. Experimental results show that action filtering provides negligible safety improvement, while observation filtering reduces near mid-air collisions by 90% and remains robust to the barrier function's tradeoff between separation distance and closing rate. These results suggest that, for policies with learned safety behaviors, preserving the policy's decision authority outperforms overriding its actions with hand-designed constraints.

Learning0 citations2026-06-20arXiv ->

Decentralized Geometric Control for Cable-Suspended Payload Transport with Adaptive Mass Estimation

Hadi Hajieghrary, Benedikt Walter, Paul Schmitt, Miguel Hurtado

Cooperative aerial transport requires controllers that respect nonlinear manifold geometry, operate without centralized coordination, and respect operational safety constraints. To address these demands, we present GPAC, a four-layer hierarchical architecture that enables $N$ quadrotors to transport a cable-suspended payload without a central coordinator or by exchanging cable states or adaptive parameters. The key insight is implicit coordination: each quadrotor independently estimates its effective load share from local cable measurements, so combined forces converge to the correct total, even without knowledge of $N$ or the payload mass; the payload position is reconstructed locally from each agent's own cable geometry, and the only inter-agent communication is a low-rate neighbor-position broadcast for collision avoidance. GPAC operates directly on the full nonlinear configuration manifold and integrates geometric position and attitude control, anti-swing regulation, an extended-state observer for wind rejection, concurrent learning-based mass estimation without persistent excitation, and a priority-ordered control barrier function (CBF)-inspired safety filter that reduces operational risk, with input-to-state safety (ISSf) margins that hold exactly under single-constraint activation. A compatibility result shows that the filter's force modifications keep the desired attitude within the almost-global stability region of the $\mathrm{SO}(3)$ attitude controller. Finally, high-fidelity simulation with flexible cables, onboard sensor fusion, and wind turbulence -- with all control and estimation loops closed through the estimator -- yields a mean payload-tracking RMSE of 33.8 cm (2.8\% coefficient of variation over 13 seeds) at a low per-agent computational cost.

Artificial Intelligence | 2 papers | 3.2% coverage
Robotics0 citations2026-07-14arXiv ->

Autonomous Tracking and Terminal Guidance of Moving Targets for Fixed-Wing UAVs

Wei-Hao Liou, Teng-Hu Cheng

This study introduces a unified control framework for fixed-wing unmanned aerial vehicles (UAVs) fitted with a pan-tilt (PT) camera, intended to perform an end-to-end mission spanning from initial target detection to accurate terminal engagement. The proposed system employs a three-phase strategy: a vision-based target acquisition phase, an NMPC-based tracking phase, and a terminal guidance phase. During tracking, the framework uses an Unscented Kalman Filter (UKF) to fuse YOLO-based visual detections with inertial measurements, enabling robust target state estimation under unknown dynamics. To ensure reliable visual contact, we introduce a constraint-aware Nonlinear Model Predictive Control (NMPC) strategy that incorporates Control Barrier Functions (CBFs) to explicitly prevent UAV self-occlusion -- a common limitation in fixed-wing tracking. Upon satisfying terminal engagement conditions, the system seamlessly transitions control to a quaternion-based Biased Proportional Navigation Guidance (BPNG) law, enforcing precise impact angle constraints. High-fidelity simulations demonstrate that the framework achieves stable, robust tracking and accurate terminal interception while strictly respecting the vehicle's dynamic limits and camera field-of-view constraints.

MPC/Planning0 citations2026-06-08arXiv ->

Who Earns the Safety? Intervention-Aware Quantum Predictive Control with Safety Attribution

Yifan Wang

Hard safety filters are increasingly placed downstream of learned controllers to guarantee constraint satisfaction at run time. Yet a filtered controller that never violates a constraint may still have learned nothing about safety: the filter can silently repair an incompetent upstream policy, so that post-filter success measures the filter, not the policy. We argue that safe policy learning should ask who earns the safety - the policy or its protective layers - and we make this question measurable. We introduce Intervention-Aware Variational Quantum Differentiable Predictive Control (IA-VQC-DPC), which (i) trains a compact variational quantum circuit (VQC) policy under a primal-dual intervention budget that penalizes reliance on a differentiable Control-Barrier-Function (CBF) projection, and (ii) is evaluated with a safety-attribution protocol that decomposes the executed-trajectory correction into a CBF term and a deployment runtime-guard term, and stress-tests the policy with guard-off evaluation. On closed-loop, high-fidelity BOPTEST building-control emulators (5 seeds, 60 episodes per method), intervention-aware training significantly lowers the quantum policy's raw pre-filter violation and total safety-layer reliance (both p < 10^-4) with no significant energy regression; at an equal approximately 400-parameter budget the quantum policy is significantly safer and more comfortable than a matched classical policy. Guard-off evaluation confirms the improvement is policy-level and exposes a valuable negative result: a learned differentiable energy head is only safe when paired with a distribution-aware runtime guard. The attribution protocol is general beyond quantum policies and buildings.

Computer Vision and Pattern Recognition | 1 papers | 1.6% coverage
Robotics0 citations2026-07-09arXiv ->

SplatCtrl: Perception-Action Coupling via Gaussian Scene Representations and Reactive Robot Control

Siddarth Jain, Ho Jin Choi

Robotic manipulators excel in structured environments but face substantial challenges in unstructured and dynamic settings. This paper presents SplatCtrl, a unified framework for real-time scene reconstruction and reactive robot motion generation to enable collision-free robotic arm control in previously unseen and continuously changing environments. Building on 3D Gaussian Splatting (3D-GS), we introduce a hybrid voxel-based filtering and dynamic Gaussian relocation strategy that supports efficient scene reconstruction from RGB-D streams while accommodating environmental changes. For safe and reactive control, we further propose a method for deriving continuous signed distance functions from isotropic Gaussians, providing stable and differentiable collision probability estimates that bridge classical distance fields with the modern implicit representation. These continuous distance metrics are incorporated into control barrier functions, resulting in a unified perception-action coupling framework that supports smooth and reliable real-time motion generation in response to scene changes. Experimental validation in simulation, on physical robot, and within shared human-robot workspace demonstrates the framework's effectiveness, achieving integrated scene reconstruction and reactive control in uncertain, and dynamic environments.

Dynamical Systems | 1 papers | 1.6% coverage
Robotics0 citations2026-06-16arXiv ->

Memory-Efficient Meta-Reinforcement Learning for Adaptive Safety-Critical Control in Adversarial Spacecraft Proximity Operations

Alejandro Posadas-Nava, Richard Linares, Minduli Wijayatunga

Autonomous spacecraft rendezvous and proximity operations (RPO) require controllers that guarantee safety under thrust constraints while minimizing fuel expenditure. Input-constrained control barrier functions (ICCBFs) provide a control method for nonlinear systems with actuation constraints that construct a forward-invariant safe set. Previous work has shown that learning class-$\mathcal{K}$ functions defining the ICCBF recursion via meta reinforcement learning (meta-RL) yields a robust, non-greedy approach to safety-critical control in RPO. This paper extends that framework further by investigating the performance of three recurrent network architectures (Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Selective State Space Model (Mamba)) and two training algorithms (Proximal Policy Optimization (PPO) and Soft Actor Critic (SAC)) to identify the best setup for tuning ICCBF class-K functions via meta-RL. In addition to cooperative test cases, performance is evaluated in the presence of adversarial behavior where the target spacecraft behaves in a way that worsens the safety of the chaser spacecraft. Results indicate that state space models such as Mamba when used with PPO achieve superior task completion, safety, and fuel-savings compared to other architectures, across all cooperative and uncooperative scenarios tested.

quant-ph | 1 papers | 1.6% coverage
MPC/Planning0 citations2026-06-08arXiv ->

Who Earns the Safety? Intervention-Aware Quantum Predictive Control with Safety Attribution

Yifan Wang

Hard safety filters are increasingly placed downstream of learned controllers to guarantee constraint satisfaction at run time. Yet a filtered controller that never violates a constraint may still have learned nothing about safety: the filter can silently repair an incompetent upstream policy, so that post-filter success measures the filter, not the policy. We argue that safe policy learning should ask who earns the safety - the policy or its protective layers - and we make this question measurable. We introduce Intervention-Aware Variational Quantum Differentiable Predictive Control (IA-VQC-DPC), which (i) trains a compact variational quantum circuit (VQC) policy under a primal-dual intervention budget that penalizes reliance on a differentiable Control-Barrier-Function (CBF) projection, and (ii) is evaluated with a safety-attribution protocol that decomposes the executed-trajectory correction into a CBF term and a deployment runtime-guard term, and stress-tests the policy with guard-off evaluation. On closed-loop, high-fidelity BOPTEST building-control emulators (5 seeds, 60 episodes per method), intervention-aware training significantly lowers the quantum policy's raw pre-filter violation and total safety-layer reliance (both p < 10^-4) with no significant energy regression; at an equal approximately 400-parameter budget the quantum policy is significantly safer and more comfortable than a matched classical policy. Guard-off evaluation confirms the improvement is policy-level and exposes a valuable negative result: a learned differentiable energy head is only safe when paired with a distribution-aware runtime guard. The attribution protocol is general beyond quantum policies and buildings.

  • IROS 202648
  • IROS 202541
  • ICRA 202646
  • CDC 202612
  • CDC 202510
  • ACC 202623
  • RAL 20264
  • RAL 202513
  • TAC 20252
IROS 2026 | 48 papers
CBF Related Papers
Robotics0 citations2026-07-17arXiv ->

Certifiable Safe Model-Based Reinforcement Learning with Control-Affine Dynamics Approximation

Hao Zhou, Yanze Zhang, Cameron Reid, Wenhao Luo

Safe model-based reinforcement learning (RL) often bridges control-theoretic analysis and RL for robots to safely explore (partially) unknown system dynamics while deriving control actions for task efficiency. The control performance and safety assurance typically rely on prior knowledge of partially modeled nominal system dynamics and the data-driven models that compensate for residual model uncertainties. However, existing methods often overlook the structure of residual model uncertainties (e.g., components affine in control), which could lead to overly conservative robot behaviors or invalid safety guarantees under the safe learning-based controllers. This paper proposes a safe reinforcement learning framework that learns control-affine dynamics with a certifiable data-driven safe policy using control barrier functions (CBF). Specifically, we first use Control-Affine Random Fourier Features (ARFF) to model robot dynamics in a control-affine form, which offers computational efficiency that scales with dataset size and reduces potential model bias for model-based reinforcement learning. Then, a model-free, efficient uncertainty quantification method using adaptive conformal prediction (ACP) is applied to quantify the uncertainty in the safety constraint arising from the learned control-affine dynamics. This allows for data-driven safety assurance amenable to principled and efficient controller synthesis with CBF. Simulation results on the cartpole and the 3D quadrotor platforms demonstrate the effectiveness of the proposed framework.

Robotics0 citations2026-07-16arXiv ->

Safe Execution of RL Policies Via Acceleration-Based CBF-QP Constraint Enforcement for Real-World Robotic Deployments

Bastien Muraccioli, Alice Cariou, Pierre-Alexandre Leziart, Mathieu Celerier, Arnaud Demont et al.

Reinforcement Learning (RL) has demonstrated remarkable capabilities for solving complex robotic control problems, but its lack of safety guarantees severely limits deployment on hardware. In particular, as legged robots and manipulators often operate near safety-critical boundaries, out-of-distribution states can lead to failure upon deployment. To address this, we introduce Acc-CBF-QP, an acceleration-based Quadratic Program (QP) safety filter using Control Barrier Functions (CBFs) that constrains any RL policy onto a safe set at runtime without modifying training. The method applies to unconstrained and Safe-RL policies, and enforces joint position, velocity, torque, and collision constraints within a unified optimization framework. A key contribution is the formulation of RL+QP tasks that regulate deviation from the RL command when constraints would otherwise be violated. We introduce a TorqueTask, minimizing torque deviation, and a Forward Dynamics Task, minimizing induced acceleration deviation, thus providing principled control over safety-performance trade-offs. Experiments on a 7-DoF Kinova Gen3 manipulator and a 19-DoF Unitree H1 humanoid, both in simulation and on hardware, highlight substantial reductions in constraint violations. On the real H1 hardware, a Safe-RL policy alone yielded 10.04 violations/s, which were reduced by 92% to 0.80 violations/s when augmented with Acc-CBF-QP. On the Kinova Gen3, Acc-CBF-QP fully eliminated violations. Nominal task performance of the RL objective is preserved in violation-free regimes. Under aggressive velocity commands on H1, Acc-CBF-QP improves execution by preventing constraint-induced shutdowns, yielding longer survival times. The full pipeline is open-source.

Robotics0 citations2026-07-01arXiv ->

Robust Operational Space Control with Conformal Disturbance Bounds for Safe Redundant Manipulation

Wenhua Liu, Fan Zhang, Qin Lin

Redundant robotic manipulators operating in constrained and human-interactive environments require accurate task-space tracking together with rigorous safety guarantees under dynamic uncertainties. Classical operational space computed torque controller (OSCTC) relies on accurate dynamic models and degrades in the presence of disturbances. In contrast, the data-driven paradigm of residual learning approximates disturbances as functions learned from full-state measurements, which are often noisy in practice, lack rigorous theoretical guarantees, and introduce additional design complexity. This paper proposes a robust OSCTC framework that integrates an extended state observer (ESO) with conformal prediction to combine model-based robustness and data-driven adaptability. The ESO estimates lumped disturbances directly in operational space without requiring full-state measurements as in residual learning, and a robust control barrier function (CBF) is constructed to enforce safety under uncertainty. However, robust CBFs require a known disturbance-variation bound to guarantee absolute safety, which often leads to conservatism in practice. To address this limitation, we further employ a sliding-window conformal prediction mechanism to estimate the bound online in a distribution-free manner, thereby achieving practical probabilistic safety guarantees. Experiments on a 7-DoF Franka Research 3 manipulator demonstrate millimeter-level tracking accuracy and real-time safe control at 1~kHz under various disturbances.

Learning0 citations2026-06-20arXiv ->

Decentralized Geometric Control for Cable-Suspended Payload Transport with Adaptive Mass Estimation

Hadi Hajieghrary, Benedikt Walter, Paul Schmitt, Miguel Hurtado

Cooperative aerial transport requires controllers that respect nonlinear manifold geometry, operate without centralized coordination, and respect operational safety constraints. To address these demands, we present GPAC, a four-layer hierarchical architecture that enables $N$ quadrotors to transport a cable-suspended payload without a central coordinator or by exchanging cable states or adaptive parameters. The key insight is implicit coordination: each quadrotor independently estimates its effective load share from local cable measurements, so combined forces converge to the correct total, even without knowledge of $N$ or the payload mass; the payload position is reconstructed locally from each agent's own cable geometry, and the only inter-agent communication is a low-rate neighbor-position broadcast for collision avoidance. GPAC operates directly on the full nonlinear configuration manifold and integrates geometric position and attitude control, anti-swing regulation, an extended-state observer for wind rejection, concurrent learning-based mass estimation without persistent excitation, and a priority-ordered control barrier function (CBF)-inspired safety filter that reduces operational risk, with input-to-state safety (ISSf) margins that hold exactly under single-constraint activation. A compatibility result shows that the filter's force modifications keep the desired attitude within the almost-global stability region of the $\mathrm{SO}(3)$ attitude controller. Finally, high-fidelity simulation with flexible cables, onboard sensor fusion, and wind turbulence -- with all control and estimation loops closed through the estimator -- yields a mean payload-tracking RMSE of 33.8 cm (2.8\% coefficient of variation over 13 seeds) at a low per-agent computational cost.

Robotics0 citations2026-03-05arXiv ->

Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation

Dian Yu, Qingchuan Zhou, Bingkun Huang, Majid Khadiv, Zewen Yang

Current Vision-Language-Action (VLA) models rely primarily on RGB perception, preventing them from capturing modalities such as thermal signals that are imperceptible to conventional visual sensors. Moreover, end-to-end generative policies lack explicit safety constraints, making them fragile when encountering obstacles and novel scenarios outside the training distribution. To address these limitations, we propose Safe-Night VLA, a multimodal manipulation framework that enables robots to see the unseen while enforcing rigorous safety constraints for thermal-aware manipulation in unstructured environments. Specifically, Safe-Night VLA integrates long-wave infrared thermal perception into a pre-trained vision-language backbone, enabling semantic reasoning grounded in thermodynamic properties. To ensure safe execution under out-of-distribution conditions, we incorporate a safety filter via control barrier functions, which provide deterministic workspace constraint enforcement during policy execution. We validate our framework through real-world experiments on a Franka manipulator, introducing a novel evaluation paradigm featuring temperature-conditioned manipulation, subsurface target localization, and reflection disambiguation, while maintaining constrained execution at inference time. Results demonstrate that Safe-Night VLA outperforms RGB-only baselines and provide empirical evidence that foundation models can effectively leverage non-visible physical modalities for robust manipulation.

Robotics0 citations2026-03-05arXiv ->

Safe-SAGE: Social-Semantic Adaptive Guidance for Safe Engagement through Laplace-Modulated Poisson Safety Functions

Lizhi Yang, Ryan M. Bena, Meg Wilkinson, Gilbert Bahati, Andy Navarro Brenes et al.

Traditional safety-critical control methods, such as control barrier functions, suffer from semantic blindness, exhibiting the same behavior around obstacles regardless of contextual significance. This limitation leads to the uniform treatment of all obstacles, despite their differing semantic meanings. We present Safe-SAGE (Social-Semantic Adaptive Guidance for Safe Engagement), a unified framework that bridges the gap between high-level semantic understanding and low-level safety-critical control through a Poisson safety function (PSF) modulated using a Laplace guidance field. Our approach perceives the environment by fusing multi-sensor point clouds with vision-based instance segmentation and persistent object tracking to maintain up-to-date semantics beyond the camera's field of view. A multi-layer safety filter is then used to modulate system inputs to achieve safe navigation using this semantic understanding of the environment. This safety filter consists of both a model predictive control layer and a control barrier function layer. Both layers utilize the PSF and flux modulation of the guidance field to introduce varying levels of conservatism and multi-agent passing norms for different obstacles in the environment. Our framework enables legged robots to safely navigate semantically rich, dynamic environments with context-dependent safety margins.

Robotics0 citations2025-12-09arXiv ->

VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer

Songqiao Hu, Zeyi Liu, Shuang Liu, Jun Cen, Zihan Meng et al.

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in generalizing across diverse robotic manipulation tasks. However, deploying these models in unstructured environments remains challenging due to the critical need for simultaneous task compliance and safety assurance, particularly in preventing potential collisions during physical interactions. In this work, we introduce a Vision-Language-Safe Action (VLSA) architecture, named AEGIS, which contains a plug-and-play safety constraint (SC) layer formulated via control barrier functions. AEGIS integrates directly with existing VLA models to improve safety with theoretical guarantees, while maintaining their original instruction-following performance. To evaluate the efficacy of our architecture, we construct a comprehensive safety-critical benchmark SafeLIBERO, spanning distinct manipulation scenarios characterized by varying degrees of spatial complexity and obstacle intervention. Extensive experiments demonstrate the superiority of our method over state-of-the-art baselines. Notably, AEGIS achieves over 50% improvement in obstacle avoidance rate while substantially increasing the task success rate by nearly 10%. All benchmark datasets, code, and supplementary materials are publicly available at https://vlsa-aegis.github.io/.

Robotics0 citations2025-10-03arXiv ->

Connectivity Maintenance and Recovery for Multi-Robot Motion Planning

Yutong Wang, Lishuo Pan, Yichun Qu, Tengxiang Wang, Nora Ayanian

Connectivity is crucial in many multi-robot applications, yet balancing connectivity maintenance and fleet traversability in obstacle-rich environments remains challenging. Reactive controllers based on control barrier functions can preserve connectivity when it is initially satisfied, but often struggle with deadlocks in cluttered environments. We propose a real-time Bézier-based constrained motion planning algorithm, namely MPC--CLF--CBF, that produces trajectories and control inputs concurrently, subject to high-order control barrier function and control Lyapunov function constraints. Our motion planner supports connectivity-aware navigation in cluttered workspaces and recovers connectivity from initially disconnected configurations and after temporary obstacle-induced separation; it also provides analytic continuous-time derivatives, facilitating its application to agile differentially flat systems such as quadrotors. In simulations with $4$--$12$ robots, it maintains $95.8$--$100\%$ graph-connected time at $20\%$ obstacle density, compared with $48.9$--$61.3\%$ for MPC--CBF, with no observed collisions. We further validate the planner in a physical experiment with $8$ Crazyflie nano-quadrotors.

Other Papers
Robotics0 citations2026-07-23arXiv ->

Beyond Episodic Evaluation: Memory Architectural Bottlenecks in Sequential Embodied Question Answering

Zikui Cai, Kaushal Janga, Tan Dat Dao, Seungjae Lee, Shivin Dass et al.

Embodied question answering (EQA) is traditionally evaluated under an episodic formulation, where agents solve each task independently and reset internal state between episodes. However, real-world robots operate continuously and must accumulate, retain, and selectively reuse information acquired from prior interactions. Despite this practical requirement, the architectural mechanisms needed to support sequential memory in EQA remain underexplored. In this work, we investigate how different memory architectures behave when EQA agents are evaluated sequentially, with multiple questions answered in the same scene while memory is carried forward across queries. We find that simply preserving existing memory is often insufficient. Agents that retain only traversability information, such as 2D occupancy maps, remember where the robot has explored but not the visual-semantic evidence needed for later questions. Agents trained on short-horizon episodic data face a different challenge: when exposed to continuous, multi-query histories, their inherited context suffers from severe temporal mismatch, rather than forming a reusable scene representation. To overcome this architectural bottleneck, we highlight the necessity of structured, spatially grounded memory: architectures that map persistent visual observations onto metric 3D geometry preserve visual-semantic evidence in a coherent scene representation. Extensive experiments in simulated environments reveal that this form of memory breaks the accuracy-efficiency tradeoff in sequential settings, simultaneously achieving higher answer accuracy and lower navigation costs. We further validate these findings on a real-world mobile robot, demonstrating that spatially grounded visual memory is critical for enabling continuous, intelligent operation in physical environments.

Robotics0 citations2026-07-23arXiv ->

GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition

Panagiotis Mermigkas, Argyris Manetas, Petros Maragos

Existing Gaussian-splatting-based monocular Simultaneous Localization and Mapping (SLAM) systems are either tailored to short sequences, are not real-time, or suffer from prohibitive GPU memory requirements, limiting their applicability in realistic, long-horizon scenarios. To address this, we present GLAM-SLAM, a real-time, decoupled Gaussian-splatting SLAM system designed for large-scale outdoor scenes. We ensure lightweight tracking using a robust, feature-based SLAM frontend, while for mapping, we adopt a structured, sparse anchor grid representation that ensures scalable operation and maintains scene coherence across long-term sequences. To satisfy the dense initialization requirements of 3D Gaussian Splatting (3DGS), we introduce a geometry-based flow-densification anchoring strategy using epipolar constraints. Furthermore, by treating mapping as a multi-scene problem, we propose a scene-partitioning strategy that introduces a strong spatial inductive bias via MLP initializations to generate localized Gaussians. We evaluate our system on the challenging, long-sequence KITTI Odometry, Oxford RobotCar, and M'alaga datasets. Extensive ablations and comparisons demonstrate a 15% improvement in reconstruction quality over the second-best performer, while maintaining real-time performance and the ability to scale to longer sequences. Code is publicly available for the benefit of the community.

MPC/Planning0 citations2026-07-23arXiv ->

Grasp, Handover, Rotate: Bimanual Object Reorientation via Compositional Diffusion and Energy-Based Optimization

Wun Lam Yeung, Wenjun Liu, Yui Cheung Yu, Zhengyan Lambo Qin, Qijin She et al.

Bimanual object reorientation - picking an object, handing it over between two arms, and placing it in a desired target pose - is valuable when direct placement from the initial grasp is infeasible due to collisions, kinematic constraints, or poor final orientation. However, achieving this under multiple competing objectives remains challenging. We introduce BiCompoDiff, a compositional diffusion and energy-based framework that jointly optimizes grasp selection, handover, regrasp, and motion planning under multiple constraints. By combining a pretrained grasp diffusion model with bimanual planning energy-based models (EBMs), our method injects gradient guidance during reverse diffusion to enforce collision avoidance, trajectory smoothness (via differentiable inverse kinematics), handover feasibility, and regrasp safety. Annealed MCMC sampling further refines grasp poses over the composite energy landscape. Experiments across diverse simulated household reorientation tasks demonstrate that BiCompoDiff achieves over 20% higher success rates and up to 37% smoother trajectories (measured by joint displacement) compared to strong sampling-based baselines. Real-world validation confirms effective sim-to-real transfer and robust performance on challenging scenes.

Robotics0 citations2026-07-23arXiv ->

Deep Reinforcement-Learning-Guided Model Predictive Control for Preventing Overtakes in Autonomous Racing

Yufei Xi, Yijie Liao, Tulga Ersal

This paper addresses defensive blocking in autonomous racing, where a vehicle must prevent a faster opponent from overtaking while operating near its dynamic limits. Different from lap-time minimization, we formulate defense as a spatial occupancy regulation problem via a hierarchical reinforcement-learning guided model predictive control framework. A Soft Actor-Critic strategic layer operates in the Frenet domain to generate geometry-aware defensive references, which are embedded into the nonlinear model predictive control formulation as spatial regularization under friction constraints. Evaluated on the Thunderhill West circuit in simulation, the framework increases average overtake time from 8.8 s to 14.6 s while significantly reducing opponent progress. Meanwhile, it allows the vehicle to utilize 83.4% of available tire force. The framework achieves a 33.3 ms mean solve time (13.9 ms std), supporting real-time high-speed adversarial interaction.

Robotics0 citations2026-07-22arXiv ->

Decentralized UAV Swarms for Ground Target Protection in GPS- and Communication-Denied Environments

Dimitria Silveria, Paulo Ricardo Marques de Araujo, Tiago Nascimento, Sidney Givigi

The presence of UAVs in military operations has recently increased, also increasing the demand for defense systems against UAV attacks. UAVs can also be used as countermeasures. Most available methods rely on UAV-to-UAV communication and global positioning. However, such resources may not be available in modern warfare scenarios. To address these limitations, we propose a pipeline for ground-target protection against UAV attacks that employs autonomous swarms of UAVs. We assume a communication- and GPS-denied environment in which the UAVs use onboard sensors to track the target and coordinate as a swarm. We developed Kalman filters to estimate the states of unknown targets and the positions of UAVs in the swarm using only relative measurements. Also, our strategy is to encircle the target of interest to maximize coverage. To achieve that, we propose a decentralized swarm encirclement technique that adapts to the target's motion. Our approach was extensively validated using real robots, demonstrating its effectiveness in detecting, encircling, and intercepting hostile UAVs.

Robotics0 citations2026-07-22arXiv ->

Towards Capability-Aware Traversability Navigation for Unstructured Environments

Gianluca Capezzuto, Felipe Tommaselli, Matheus P. Angarola, Ricardo V. Godoy, Marcelo Becker

Estimating traversability in unstructured environments requires conditioning on robot embodiment, as the same terrain can be traversable for one platform and unsafe for another. Existing methods often transfer predictions across morphologies through late-stage trajectory filtering rather than encoding platform constraints in the learned representation. We propose Capability-Aware Traversability (CAT), a framework that embeds physical limits directly into the spatial feature space. CAT grounds dense supervision masks in physical trajectories through an interactive annotation pipeline and modulates semantic terrain maps with robot-specific traversability vectors through Spatially-Adaptive Denormalization (SPADE) blocks. Across human-annotated and trajectory-aligned datasets, CAT leads all ranking-based metrics, improving AUROC by 11.0% on physically executed trajectories and AUPRC by 15.8% on human traces over the strongest baseline. Ablations show that spatial conditioning and per-robot prototypes produce capability sensitivity beyond generic path prediction. Deployments on a legged quadruped and a wheeled skid-steer demonstrate embodiment-aware obstacle avoidance on embedded hardware at 4.8 Hz.

Robotics0 citations2026-07-22arXiv ->

ODeform: Learning Continuous 4D Motion for Shape Deformation with Neural ODEs

Yordanka Velikova, Mahdi Saleh, Liming Kuang, Benjamin Busam

Modeling continuous object deformation is important for many computer vision and robotics tasks, such as manipulation and simulation. Existing approaches rely on learning-based methods or physics simulators to model shape deformations. However, these approaches either use discrete time steps or are too computationally intensive for real-time applications. We present ODeform, a novel extension of Neural Ordinary Differential Equations to continuous 4D dynamics of deformable objects in 3D space. Our method transforms 3D point clouds and physical conditions (like material properties) into a unified latent space. By solving the resulting ordinary differential equations over time, we model deformations as continuous flows within this learned embedding, eliminating the need for discrete time steps while maintaining computational efficiency. We evaluate our approach on unseen physical parameter configurations, showing improved motion prediction accuracy over baseline methods. Our experiments further demonstrate a successful transfer to real 3D captured objects with novel shapes, along with effective interpolation and extrapolation of the learned dynamics. Our code and data will be made publicly available.

Robotics0 citations2026-07-22arXiv ->

V2F: Vision-Informed Grasp Force Prediction for Damage-Aware Robotic Handling of Date Fruits

Shahd Shami, Obadah Wali, Eric Feron, Shinkyu Park

This paper presents a vision-informed grasp force prediction framework for robotic handling of date fruits. Addressing the dual challenge of high detachment forces and low bruise thresholds, we first conduct mechanical characterization on date samples to define a safe grasping envelope and quantify the relationship between fruit geometry and bioyield stress. In this work, we develop a Vision-to-Force (V2F) pipeline that combines computer vision-based segmentation, active-contour refinement, and geometric feature extraction with a physics-informed residual neural network that augments a Hertz contact equation. The resulting model maps non-contact visual descriptors and cultivar metadata to predict a safe grasp force with mean validation performance of $R^2 \approx 0.7$ across unseen cultivar groups, which is a good result given the inherent mechanical variability of biological tissue. Experimental validation using a gripper and load cell indicates that the predicted forces enable stable manipulation of different types of date fruits, with residual deformations below 1 mm and no observable damage. These results show that pre-emptive, vision-driven force estimation% can replace slow and potentially damaging tactile exploration , enabling safer robotic handling of fragile fruits.

Robotics0 citations2026-07-21arXiv ->

Bayesian Retraction Optimization for Tissue Attachment Mapping in Surgical Dissection

Shing-Hei Ho, Bao Thach, Toan Vo, James M. Ferguson, Alan Kuntz

With growing surgeon shortages, automating surgical sub-tasks such as tissue dissection offers a promising step toward reducing workload and expanding patient access. Prior work has relied on hand-crafted incision policies that cannot quantify uncertainty or has relied on simulation-based methods that require strong modeling assumptions. We instead view tissue attachment identification as an inherently probabilistic problem and propose a Bayesian approach that avoids explicit tissue modeling. Our method uses a Sequential Bayesian Hilbert Map (SBHM) to represent the likelihood that each tissue point is attached to the underlying resection surface. An ensemble of learned classifiers predicts attachment likelihoods from spatial data acquired during robotic tissue retraction, with each classifier serving as a noisy information source to update the SBHM. To plan the next retraction, we devise Bayesian Retraction Optimization (BRO) to select the most informative action under safety constraints. As the SBHM refines over time, regions with high attachment likelihood are selectively incised. We validate our method in simulation across diverse tissue geometries and acquisition strategies, and demonstrate zero-shot transfer to real robotic dissection experiments.

MPC/Planning0 citations2026-07-21arXiv ->

NGPS: GPS-Denied Aerial Geo-Localization and 2.5D Reconstruction via Deep Satellite Image Matching and Multi-Rate Sensor Fusion

Sanket Sharma

We present NGPS (Next-Generation Positioning System), a visual geo-localization framework for high-altitude UAVs that provides GPS-free absolute positioning by matching down-facing images to georeferenced satellite imagery with deep features. The system combines (1) adaptive confidence-weighted UKF fusion, where NGPS covariance is modulated by RANSAC inlier ratio, reprojection error, and match confidence; (2) velocity-predictive kernel extraction, using VIO velocity to predict the satellite search region; and (3) an asynchronous multi-rate temporal priority queue that interleaves absolute position (1-2 Hz), VIO (10-20 Hz), and IMU (100-200 Hz) updates in chronological order. Globally optimized poses from VINS pose-graph optimization, anchored by NGPS corrections, further enable real-time 2.5D georeferenced orthomosaic reconstruction. On five flight sequences (60-150 m AGL), NGPS achieves 2.94 m position RMSE, with worst-case ATE 6.04 m at 150 m AGL and 2 m/s, yielding a 3.5x improvement over standalone monocular VIO. The system runs in real time on an NVIDIA Jetson Orin NX. Part of the implementation is open-sourced at https://github.com/snktshrma/ngps_flight.

Robotics0 citations2026-07-21arXiv ->

MVP-Tac: A Miniaturized Dual-Modal Vision and Photoelastic Tactile Sensor for Robot-Assisted Minimally Invasive Surgery

Md Rakibul Islam Prince, Jaeeun Kim, Yuhao Zhou, Mason Vrshek, Shivani Reddy Sama et al.

Robot-assisted minimally invasive surgery (RMIS) offers major benefits over open and conventional laparoscopic procedures, yet it still lacks tactile feedback for palpation while operating under strict requirements to preserve reliable vision for navigation and safety. In practice, visual feedback is indispensable, and tactile solutions that cannot coexist with vision are difficult to translate into RMIS tools. To address both needs, we introduce MVP-Tac, a compact, vision-based tactile sensor that provides co-located vision and tactile sensing. MVP-Tac uses reflective photoelastic imaging: a thin photoelastic elastomer produces stress-dependent interferograms under contact that are captured by an embedded camera through a miniaturized reflective polariscope. A semi-transparent membrane and controllable illumination enable switching between visual mode and tactile mode, enabling tactile perception without sacrificing vision. We validate MVP-Tac through force calibration in the 0 to 2 N range and demonstrate its potential for tumor palpation via video-based hardness classification on tissue phantoms, achieving 97% accuracy for exposed-tumor classification and 92% accuracy for subdermal-tumor classification. Finally, we conduct a simulated colonoscopy to validate both visual and tactile modalities in a constrained lumen, including vision-guided 3D photomapping of the luminal wall and in situ hardness classification of localized nodules. Overall, MVP-Tac provides a practical path toward restoring clinically useful palpation in RMIS while maintaining essential visual feedback. The design, fabrication, and firmware of MVP-Tac are open-sourced at https://mvp-tac.github.io/

Robotics0 citations2026-07-20arXiv ->

Two-Stage Extrinsic Calibration of a Static Line-Scanning Lidar with a Rotary Platform

Vikram Shree, Hike Danakian, Long Nguyen, Rajanish Gokidi, Patrick Nercessian

A line-scanning lidar yields range and azimuth values in a fixed plane. To perceive surrounding objects in 3D, there must be relative motion between the lidar plane and the object. Thus, using a rotating base-platform is promising for industrial applications where objects need to be scanned or inspected precisely, and is the main focus of this work. In the rotary platform setup, a 3D point cloud of an object can be constructed if the axis of rotation and the precise motion about that axis are known. However, this setup gives rise to the following problem: how can the axis of rotation of the platform be accurately identified with respect to the lidar coordinate system? It is referred to as the calibration problem in the robotics community. Any inaccuracy in this transformation directly affects the quality of the reconstructed point cloud, leading to misrepresentation of the object of interest. In this work, we explore automated approaches to statically and dynamically estimate the transformation of a rotary platform's axis of rotation with respect to a static line-scanning lidar. The proposed algorithms have been validated on real-world datasets obtained from a custom made rotary platform and an FMCW lidar, and their convergence characteristics are studied for various initial conditions.

Robotics0 citations2026-07-20arXiv ->

Recti-Q: Feature-Space Rectification for Out-of-Distribution-Robust Quantized Perception in Edge Robotics

Hamidreza Yaghoubi Araghi, Parastoo Pilevar, Ming C. Lin

Robotic perception pipelines increasingly rely on large vision backbones deployed on SWaP-constrained edge platforms, making post-training quantization (PTQ) attractive for real-time inference. However, while PTQ often preserves clean in-distribution accuracy, we show that it can substantially degrade reliability under deployment-relevant distribution shifts (e.g., sensor noise, severe weather, and novel operating environments), creating a Quantization-Induced Robustness Gap. Across foundational vision benchmarks (ImageNet-C and PACS), 4-bit PTQ models exhibit pronounced robustness degradation despite negligible ID accuracy loss. To address this, we propose Recti-Q, a lightweight feature-space rectification framework that freezes the quantized backbone and trains a small classifier-head LoRA adapter using only source data. Recti-Q is architecture-agnostic across CNNs and Transformers, supports efficient teacher-free training, and recovers a significant portion of the lost robustness, in some cases matching or exceeding FP32 performance. At less than 1% parameter overhead (as small as 6 KB), Recti-Q preserves over 99% of PTQ memory savings, adds negligible compute, and enables low-bandwidth Over-The-Air (OTA) resilience patching for deployed robotic fleets operating in unpredictable physical environments.

Robotics0 citations2026-07-20arXiv ->

DASH Robot: Minimalistic Design and Optimal Aerial-Terrestrial Locomotion via Contact-Implicit Control

Ryan Gomes Paiva, Conrad Ho, Jiarong Kang, Kunzhao Ren, Xiangru Xu et al.

We present a novel and minimalistic design of an aerial-terrestrial robot DASH: Ducted Aerial Spring Hopper. The goal is to enable both aerial and ground locomotion capabilities on a unified mobile robot that is mechanically-minimalistic, locomotion-versatile, and energy-efficient. We propose an organic integration of ducted fan co-axial body with a springy leg at the bottom for realization. The ducted fan module provides thrust-vectoring as the main actuation for agile flying; when it is combined with the light-weight spring leg, the robot realizes highly efficient ground hopping with energy circulation. Moreover, to realize optimal locomotion with two modes, we employ a contact-implicit model predictive controller to automatically choose locomotion modes and actuation. We successfully validated the design and control of DASH through a range of tasks, including periodic hopping, aerial flight, and mode-free locomotion with autonomous mode transitions during obstacle traversal.

Robotics0 citations2026-07-20arXiv ->

Beyond Fixed Goal Delivery: Online POMDP Planning for Target Interception in Crowds

Himanshu Gupta, Kelvin Aladum, Nisar Ahmed, Bradley Hayes, Zachary Sunberg

Target interception in crowded environments requires reaching a moving objective while navigating among multiple uncertain human agents. Since human navigation intent is not directly observable, the robot must reason over multiple possible future interaction outcomes. We formulate interception in crowds as a partially observable Markov decision process and solve it online using tree search under a fixed computational budget. In this setting, the action-space structure directly shapes the search tree and how computational effort is allocated. We perform a controlled comparison between a sequential path-speed planner, which first plans a spatial path and then modulates speed along it, and a unified planner that jointly branches over steering and speed within tree search. Across simulations with up to 200 humans, both approaches perform similarly at low crowd density but diverge sharply as density increases. At the highest crowd density, the sequential planner has a safe-interception rate 31 percentage points lower and requires 44% more time than the unified steering-speed planner, revealing a structural limitation of spatial restriction. Project webpage: https://tic-planning.github.io/

Learning0 citations2026-07-20arXiv ->

Value-Aware Prediction for Robust Multi-Agent Coordination Under Communication Loss

Kemal Devrim Kafadar, Eren Özaltun, Mahmud Efnan Şanlı, Feyza Orak, Emirhan Gazi et al.

Robust multi-agent coordination relies heavily on inter-agent communication, which is frequently disrupted by physical and environmental constraints in real-world deployments. To maintain operation during these intermittent communication failures, agents can employ internal prediction models to estimate missing shared state information. However, predictors trained with standard reconstruction objectives treat all transitions equally. In a Reinforcement Learning context, this forces the model to waste capacity learning stochastic exploration noise and the outdated dynamics of suboptimal policies. In this paper, we propose a value-aware extension of Multi-Agent Observation Sharing under Communication Dropout (MARO) to patch communication gaps; we refer to this method as Value-Aware MARO. By dynamically weighting the predictor's loss function using advantage estimates derived from the underlying actor-critic architecture, our objective explicitly couples the predictor's learning process to the policy's evolution. This formulation focuses the model's capacity on the intentional, high-return dynamics actively reinforced by the agents. We evaluate our framework on several tasks within the Multi-Agent Particle Environment under varying communication reliability levels. Experimental results demonstrate that our approach maintains performance under declining communication reliability, particularly below 40%. While our method performs comparably in tasks where the baseline already maintains high coordination, our value-aware weighting effectively prevents the performance collapse observed in the standard predictor during high-attrition scenarios. In these environments, our method achieves an average improvement in mean returns of more than 20% and reduces performance variance by a mean of 64.7% compared to the standard unweighted baseline.

Robotics0 citations2026-07-20arXiv ->

Task-Space Constrained Stochastic Trajectory Optimization for Time-Optimal Forestry Crane Motion Planning

Marc-Philip Ecker, Christoph Fröhlich, Bernhard Bischof, Wolfgang Kemmetmüller, Tobias Glück

Efficient, collision-free, and time-optimal motion planning is a fundamental requirement for autonomous forestry cranes operating under hydraulic pump-flow constraints. The Via-Point-based Stochastic Trajectory Optimization (VP-STO) algorithm has demonstrated near-time-optimal hybrid motion planning in this domain, but requires a fixed terminal joint configuration specified prior to optimization. For kinematically redundant manipulators such as forestry cranes, this pre-commitment to a single inverse kinematics solution restricts the planner's ability to exploit redundancy, particularly under the nonlinear, globally coupled pump-flow constraint where admissible joint velocities depend on their combined hydraulic demand. This paper presents TSC-VP-STO, a task-space-constrained extension of VP-STO that replaces the strict terminal joint-space constraint with a task-space constraint, jointly optimizing the trajectory and the redundant degrees of freedom of the terminal configuration. This enables the planner to adapt end configurations to the environment-dependent motion and hydraulic flow allocation, yielding more balanced pump utilization and shorter trajectory durations. We formalize the approach through a configuration space decomposition and derive a concrete reachability constraint for the forestry crane kinematics. Experimental evaluations across multiple planning targets and via-point configurations demonstrates a reduction on trajectory durations by 12-15% on average and improved pump-flow utilization compared to the baseline VP-STO. The practical applicability of TSC-VP-STO is validated through real-world deployment on a forestry crane, including a full log-loading cycle.

MPC/Planning0 citations2026-07-20arXiv ->

Lifelong Multi-Subsystem Pickup and Delivery with Buffer-Limited Handover Stations

Chuanlong Zang, Isabelle Barz, Anna Mannucci, Philipp Schillinger, Florian Lier et al.

Coordinating payload transfers between subsystems is a critical challenge in lifelong Multi-Agent Pickup and Delivery (MAPD). We study systems where agents are confined to separate regions and must exchange payloads through shared handover stations. These stations, equipped with single docks and finite buffers, are inherently vulnerable to blocking and starvation. We formalize this problem as Multi-Subsystem MAPD with Buffer-limited Handover Stations (MS-MAPD-BHS). We then propose Handover-Aware Reservation and Routing (HARR), an online controller that couples per-subsystem planners. HARR uses a shared dock reservation calendar and a deterministic rolling-horizon projection of buffer occupancy to coordinate actions. A candidate route is accepted only if its dock interval is free and the resulting buffer occupancy projection remains within capacity. Under perfect execution, these checks ensure collision-free dock use and buffer-safe committed operations within the reservation horizon. In simulation, HARR achieves up to 77% higher throughput and 92% lower backlog than a fixed-dock ablation at moderate load, while also reducing planning time relative to a coupled station-aware Token Passing baseline. These results show that explicit interface coordination substantially improves stability in modular multi-subsystem transport.

Robotics0 citations2026-07-19arXiv ->

DeeperRadar: End-to-End MIMO Radar Design and Multi-Modal Fusion for Autonomous Vehicle Perception

Eli Goldenshluger, Barak Pinkovich, Chaim Baskin

DeeperRadar is a radar-centric, sensor-stack-conditioned framework that co-designs radar sensing and multi-modal 3D detection for autonomous mobility by learning a sparse acquisition pattern end-to-end with the fusion model. A learnable MIMO design module is trained end-to-end within a fusion network that operates directly on raw radar ADC data together with camera images and LiDAR point clouds. During training, the design module is supervised by the other sensors, enabling the system to learn both which receiver antennas to activate and the effective number of them. At deployment, the design module is removed and replaced by the learned sparse subsampling mask, leaving the downstream model architecture unchanged. Evaluated on the RADIal dataset, DeeperRadar discovers sparse, task-aware radar configurations that match or exceed full-array baselines while using fewer receivers, potentially reducing radar cost and integration complexity. These results show that learned optimal MIMO radar design depends on the fusion stack and the downstream perception task.

Theory0 citations2026-07-19arXiv ->

Multi-Resolution Voxelized Map-Based Stereo Visual-Inertial Odometry

Shuyi Pan, Hangtian Wang, Zhaoxing Zhang, Chengliang Zhang, Zikang Yuan et al.

Incorporating prior maps significantly enhances the accuracy and robustness of pose estimation in visual-inertial odometry (VIO). However, the large data volume of such maps, combined with limited transmission bandwidth, makes it impractical to continuously load local maps onto an edge device. In this paper, we propose a multi-resolution prior map construction method and a corresponding map-based VIO system. The prior map is voxelized at multiple resolutions, with each voxel retaining only a single map point. During online VIO operation, a cone-shaped indexing strategy associates 2D features on the edge device with 3D map points. The cone's intercept is determined by the distance from the current position to the 3D points, enabling the selection of the appropriate resolution level and the retrieval of the unique map point within the corresponding voxel via a 3D digital differential analyzer (DDA) algorithm. This approach minimizes both the volume of data required for transmission and the computational load during data association. Extensive experiments on two public datasets demonstrate that our system achieves accurate pose estimation while requiring minimal data transmission.

Robotics0 citations2026-07-18arXiv ->

GLidE-SLAM: GL-Accelerated Indirect-Direct Embedded SLAM

Carlos A. Pinheiro de Sousa, Heiko Hamann, Oliver Deussen

With the growing demand for robotics, autonomous drones, and wearable extended reality systems, the deployment of Visual SLAM on embedded devices remains challenging. Tracking must sustain high frame rates while preserving compute resources for map extension and maintenance. This paper presents GLidE-SLAM, a monocular hybrid indirect-direct framework that addresses this by architectural separation: the system performs GPU-accelerated direct tracking on intermediate frames, while reserving the full indirect pipeline for map extension and global consistency. We leverage highly parallel image-alignment operations for pose-only estimation without depth optimization or map point creation, making the workload suitable for GPU offloading and freeing CPU resources for backend tasks. We implement the direct tracker using vendor-agnostic OpenGL ES~3.1 compute shaders, enabling deployment across a broader range of commodity embedded platforms without requiring CUDA support. To our knowledge, this is the first complete direct photometric pose estimator realized via compute shaders for embedded-class devices. Experiments on target platforms demonstrate up to 9$\times$ higher frame rates than the CPU-only baseline while maintaining trajectory accuracy and improving practical deployment across commodity resource-constrained hardware.

Robotics0 citations2026-07-17arXiv ->

Differentiable Reinforcement Learning for Path Tracking by an Agile Fish-Like Robot

Prashanth Chivkula, Kartik Loya, Venkata Ravindhra Reddy Varikuti, Phanindra Tallapragada

Fish-like swimming has inspired the design of several dozens if not hundreds of bioinspired robots in the last few decades. But the control and motion planning of such robots has been challenging due to the poorly modeled fluid-structure interaction and the nonlinear underactuated dynamics of such robots. While reinforcement learning has allowed significant advances in the context of ground and aerial robots, the lack of a suitable simulation environment with appropriate computational speed and accuracy have prevented similar progress for fish-like robots. We address this two-fold problem by developing a simulation platform that approximates the motion of our fish-like robot with computational efficiency. Then the motion control and path tracking by the robot is performed using PID control where the (variable) gains are learned using back propagation through time and training on a curriculum. The policy learned in the simulation is then applied on the physical platform, demonstrating an excellent match.

Robotics0 citations2026-07-17arXiv ->

PIXIE: A Zero-Shot texture-invariant 6D pose estimation framework for unseen objects with assembly defects

Leon Jungemeyer, Alejandro Magaña, Gautham Mohan, Matthias Karl, Daniel Werdehausen

6D pose estimation remains a key challenge in robotics and computer vision, particularly in industrial environments. The deployment of currently available data-driven methods is often limited by resource-intensive data pipelines, reliance on textured 3D models, and sensitivity to geometric deviations caused by damages or assembly defects. We present PIXIE, a zero-shot framework that estimates the 6D pose of an object from an RGB image using only an untextured 3D model. Synthetic depth and normal maps are rendered from sampled reference viewpoints and matched to the query image via a pretrained cross-modality feature matcher. Matched keypoints are back-projected to obtain 2D--3D correspondences for PnP-based pose estimation. Relying exclusively on geometry makes the method inherently robust to lighting and texture variation, while correspondence filtering handles geometric deviations between the model and physical object. We evaluate on widely-used public benchmarks, reporting state-of-the-art results on texture-less objects without object-specific training, and introduce a novel dataset with assembly defects, texture variations, and occlusion to demonstrate real-world applicability.

Robotics0 citations2026-07-17arXiv ->

DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction

Jehun Kang, Jungha Wang, Youngjun Hwang, David Hyunchul Shim

Multi-Task Learning (MTL) in robotics perception systems supports comprehensive 3D spatial scene understanding by integrating semantic segmentation and depth estimation. While Vision Foundation Models (VFMs) are increasingly adopted as robust feature encoders, existing decoding strategies present a critical bottleneck. To address this, we propose DPNeXt, a streamlined multi-scale feature fusion decoder and efficient alternative to the standard Dense Prediction Transformer (DPT). DPNeXt uses dual depthwise separable inverted bottlenecks to improve frozen VFM utilization through fusion-centric decoding and independent task modularization. To further mitigate negative inductive transfer between tasks, we introduce the Multi-Task Boundary Guidance (MTBG) strategy. Unlike prior boundary-aware methods that add fusion modules or gating, MTBG applies symmetric boundary-focused supervision to encourage geometric consistency without extra annotation or inference cost. Experiments on Cityscapes show that DPNeXt-S outperforms prior state-of-the-art (SOTA) MTL models, while DPNeXt-B further improves the overall performance and achieves the best results among the compared methods. On NYUv2, DPNeXt-B also achieves the best semantic segmentation and depth estimation results among the compared methods while requiring substantially fewer trainable parameters than prior large-scale MTL models. Compared with the standard DPT, DPNeXt-S reduces trainable parameters by 78.6% and achieves the fastest inference speed among the compared models on resource-constrained laptop hardware. The source code, model checkpoints, and a demo video will be made available at https://github.com/kangjehun/DPNeXt.

Robotics0 citations2026-07-17arXiv ->

Embodied Active Learning under Limited Annotation and Navigation Budget for Object Detection

Hadrien Crassous, Mohamed Yassine Kabouri, Minahil Raza, Joni Pajarinen, Riad Akrour

This paper studies how to adapt a computer vision object detector to an unknown environment under both a robot navigation time and annotation budget constraint. Our approach selects informative robot trajectories and image samples to retrain the detector, explicitly targeting its failure cases. Formally, the approach is an embodied variant of batch active learning, where at each round an agent has a limited navigation budget to collect candidate samples and a limited annotation budget for the most relevant images. We leverage spatial consistency to identify images with inconsistent labels, which are likely to provide the greatest improvement to the vision model. We evaluate the approach using different active learning objectives on large scenes from the AI2-THOR simulator and on a real-world setup using a Boston Dynamics Spot robot with the real-time object detector YOLOv5. Through comparison against several baselines, our experimental results show that spatial inconsistency helps guide the agent and select relevant images without external supervision, achieving the highest detection accuracy at the end of the adaptation process under the same budget. The open-source project can be found at https://mkabouri.github.io/embodied-active-learning-od

Robotics0 citations2026-07-17arXiv ->

Beyond Frontiers: Scene-Anomaly Guided Autonomous Exploration

Akash Kumbar, Abhinav Raundhal, Madhava Krishna

Autonomous exploration of unknown 3D environments is traditionally driven by coverage-maximizing geometric heuristics. However, these methods typically determine exploration targets without considering the underlying structural context. This leads to inefficient trajectories often limiting the fidelity of the final 3D reconstruction. To bridge the gap between spatial coverage and reconstruction quality, we introduce a novel paradigm: reframing exploration as a geometric anomaly minimization problem. We present SCAGE: SCene Anomaly Guided Exploration, a novel autonomous exploration framework that operates directly on unstructured 3D point clouds. Instead of blindly chasing volumetric boundaries, we equip the robot with a foundational understanding of standard indoor architecture. As the robot navigates, it continuously evaluates its live 3D observations against these learned expectations. When the incoming geometry contradicts the learned priors of a typical indoor environment, such as a fragmented wall or a partial table, the system flags these regions as scene anomalies. These geometric inconsistencies act as a guiding signal, naturally drawing the robot to investigate and resolve these structural anomalies from optimal vantage points. By actively targeting poorly reconstructed regions rather than just empty space, our approach seamlessly couples spatial discovery with high-fidelity mapping. Extensive evaluations demonstrate that SCAGE achieves superior volumetric coverage (~90% in all scenes) and higher 3D reconstruction quality compared to state-of-the-art baselines.

Robotics0 citations2026-07-17arXiv ->

Event3R: Asynchronous-to-Global 3D Reconstruction from Event Camera via Spatial-Temporal Feature Aggregation

Jian Huang, Haotian Shen, Xinhao Lou, Chengrui Dong, Wenpu Li et al.

Robust 3D reconstruction is essential for robotics and embodied perception. Recent feed-forward approaches such as DUSt3R have demonstrated impressive progress in dense 3D reconstruction from RGB images, achieving global geometric consistency and strong generalization. However, extending such dense 3D reconstruction to event cameras remains challenging due to their asynchronous, sparse, and highly dynamic nature, as well as the lack of large-scale, well-labeled datasets. In this work, we introduce Event3R, a feed-forward framework that directly maps asynchronous event streams to globally consistent 3D point clouds. Event3R represents incoming events as spatial-temporal voxels, enabling time-aware feature integration through a temporal attention module that enhances the module's temporal feature learning. To further strengthen temporal representation learning and reduce reliance on labeled data, we propose a Masked Bin Modeling (MBM) strategy for self-supervised pre-training, enabling robust temporal representation learning with minimal labeled data, and retain it as an auxiliary fine-tuning objective. In addition, contrastive alignment and consistency regularization losses are incorporated during fine-tuning to reinforce structural correspondence and temporal coherence across views. Extensive experiments on both synthetic and real-world benchmarks demonstrate that Event3R achieves robust, temporally consistent, and globally aligned 3D reconstructions, significantly outperforming existing event-based methods.

Robotics0 citations2026-07-17arXiv ->

A Generative Partially Specified Finite State Machine Approach to Complex Behaviour Planning

Kalana Ratnayake, Michael Pritchard, David Hinwood, Maleen Jayasuriya, Damith Herath

Autonomous robots operating in dynamic environments require behaviour planning systems that combine reactivity, interpretability, and adaptability. While Large Language Models have been successfully integrated with Behaviour Trees for dynamic replanning, Finite State Machines, despite their widespread adoption and computational efficiency, remain unexplored for generative approaches. We propose a Generative Partially Specified Finite State Machine (GPSFSM) neurosymbolic architecture that utilises the symbolic and semantic structure of FSMs, including states and event-triggered transitions, to implement Behaviour Planning. This paper introduces the first GPSFSM framework for robotics, featuring Fabric, an FSM engine that parses, validates, and executes behaviour plans that contain Sequential, Recovery, Parallel-Any, and Parallel-All control structures. We extend the Capabilities2 package in ROS2 with an asynchronous event system for behaviour chaining and runtime parameter injection for configurable execution, addressing the ad-hoc function representations that limit current generative systems. PromptTools provides a unified ROS 2 interface to local and cloud LLMs, with prompt buffering, enabling dynamic asynchronous composition of task and context information. Together, these components enable standardised semantic capability descriptions for robot-agnostic development. Experimental evaluation on navigation tasks demonstrates that our GPSFSM approach achieves consistently higher plan-generation success rates than the state-of-the-art BTGenBot system, particularly excelling in zero-shot scenarios where BTs typically struggle, while maintaining comparable or lower planning latency to frontier LLMs. We also demonstrate that our system can generate complex behaviours. We release an open-source ROS2 stack that makes generative FSM planning practical and reproducible for robotic systems.

Robotics0 citations2026-07-17arXiv ->

Scalable Open-Source Visuotactile Sensor for 6-Axis Contact Wrench Estimation in Tensegrity Robots

Wenzhe Tong, Jonathan Mi, Xili Yi, Nima Fazeli, Xiaonan Huang

This paper presents a scalable, open-source visuotactile sensing system for tensegrity robots that enables six-axis wrench estimation and contact detection. The proposed endcap sensor integrates an elastomeric shell, a 3D-printed thermoplastic polyurethane (TPU) interface, and a rigid base housing an embedded camera and LED illumination ring. A novel gyroid-infill bonding technique is introduced to form a durable elastomer-TPU interface without adhesives, yielding a lightweight and modular design compatible with large-scale tensegrity structures. A tactile-to-wrench neural network maps shear vector fields to six-dimensional force and torque measurements. Experimental results demonstrate accurate and stable wrench estimation with a mean squared error (MSE) of 0.1531 on static validation data and out-of-domain generalization under dynamic motion. Furthermore, full-system integration on a 12 kg tensegrity robot confirms the sensor's ability to reliably identify ground contacts. The system substantially improves the practicality of tactile feedback for tensegrity robots, offering a low-cost, reproducible, and physically interpretable pathway toward contact-aware proprioception and state estimation. Open source files are available at \href{https://github.com/Jonathan-Twz/tensegrity-gelfoot}{github.com/Jonathan-Twz/tensegrity-gelfoot}

Robotics0 citations2026-07-17arXiv ->

A Model-Based Decoupling Strategy for Proprioception and Contact Sensing in an Architected Soft Manipulator

Francesco Stella, Annan Zhang, Cosimo Della Santina, Josie Hughes, Daniela Rus

Soft continuum robots require embedded sensing for proprioception and contact detection, yet integrating sensors into sparse, highly deformable architected structures remains challenging. We present a model-based strategy that decouples proprioceptive and contact signals from a common set of fluidic pressure sensors embedded in a soft architected segment. Each segment of the Innervated Trimmed Helicoid (ITH) contains six air channels routed in a localized zigzag pattern along the circumference. With only three principal kinematic degrees of freedom (axial compression, bending in x, bending in y), the six pressure readings form an overdetermined system. A piecewise constant curvature model maps pressures to shape, and Huber regression identifies outlier channels whose residuals indicate external contact. On a single ITH segment, this approach achieves proprioceptive shape estimation with a relative bending error of 0.11 +/- 0.02 and a contact detection rate of 97% across 178 trials. We integrate eight ITH segments into Air-Helix, a tendon-driven soft continuum manipulator, and present exploratory whole-arm demonstrations that include tactile teaching by demonstration, admittance-controlled force regulation, and tactile object reconstruction. The results suggest that localized fluidic innervation combined with model-based redundancy resolution is a practical path toward concurrent proprioception and contact sensing in architected soft robots.

Learning0 citations2026-07-16arXiv ->

VTAP Gripper: Synergizing Fingertip Sensing and a Visuo-Tactile Active Palm for Dexterous In-Hand Manipulation

Yuhao Zhou, Sheeraz Athar, Zhixian Hu, Binghao Huang, Yunzhu Li et al.

This paper presents a tactile-reactive gripper that integrates a Visuo-Tactile Active Palm (VTAP) and compliant, reconfigurable fingers equipped with tactile array sensors. The design exploits structured finger-palm synergy and multi-modal perception to achieve both robust grasping and fine manipulation. The actuated bi-modal palm seamlessly combines long-range visual localization with contact-rich tactile feedback, substantially extending the system's manipulation capability. To bridge the embodiment gap between human hand motion and the heterogeneous three-finger structure, we further propose a staged, gesture-conditioned retargeting framework for dexterous teleoperation. Extensive experiments validate the system across a range of challenging tasks: reactive grasping of YCB and fragile objects, in-hand syringe reorientation and plunger actuation, singulation of clustered objects down to 3 mm in diameter, and vision-tactile peg-in-hole insertion. Results demonstrate that high manipulation performance can be achieved through coordinated finger-palm interaction and multi-modal sensing, without resorting to high degrees of freedom anthropomorphic designs. The VTAP gripper and its retargeting framework offer a practical reference architecture for dexterous gripper design, manipulation, and contact-rich data collection in support of learning-based approaches. Project webpage: https://yuhochau.github.io/vtap/.

Robotics0 citations2026-07-16arXiv ->

NeuroCommitSSM: Decision-Centric Shared Autonomy for Safe Assistive Manipulation via EEG-EMG-ET Commit Readiness

Tipu Sultan, Param Sangani, Kody Cool, Pascal Sikorski, Guangping Liu et al.

We present NeuroCommitSSM, a decision-centric framework that models when to execute, not just what to do, for safe commit-to-execute control in assistive robotic manipulation. NeuroCommitSSM predicts a continuous commit-readiness score c_t in [0,1] from synchronized electroencephalography (EEG), electromyography (EMG), and eye-tracking (ET), and converts it into discrete commit events through dwell and hysteresis filtering. A three-state finite-state supervisor, HOLD-ASSIST-COMMIT (HAC), gates execution by requiring both a sustained commit-readiness signal from the neural model and real-time perception and robot-state feasibility, including target visibility, inverse kinematics solvability, and collision-free planning, before initiating motion. We evaluate the framework on N=32 subjects performing five activities of daily living (ADL) tasks aligned with the International Classification of Functioning, Disability and Health (ICF), using leave-one-subject-out (LOSO) cross-validation and seven sensor-dropout scenarios (S0-S6). NeuroCommitSSM achieves 0.950 action-balanced accuracy with 0.75 false commit events per 1000 REST windows (FP/1k REST), and maintains low false commits and stable state transitions under sensor loss. For example, in the EEG-only condition, it achieves 0.785 balanced accuracy and 0.29 FP/1k REST, whereas the Temporal Convolutional Network baseline produces 99.95 FP/1k REST under the same condition. Hardware-in-the-loop (HIL) validation on a Kinova Gen3 arm shows that feasibility-checked execution reduces false starts and decision instability without sacrificing task success. Supplementary materials, including code, datasets, videos, and additional analyses, are available at https://madibabaiasl.github.io/NeuroCommitSSM/.

Robotics0 citations2026-07-16arXiv ->

Catch, Throw, Repeat: Planning for Human-Robot Partner Juggling

Jonathan Rainer Lippert, Kai Ploeger, Abir Chowdhury, Hermann Müller, Jan Peters et al.

Dynamic object exchange between humans and robots remains a challenging problem due to uncertainty in perception, timing, and contact-rich interaction. Human-robot juggling represents a particularly demanding instance of this problem, requiring precise real-time coordination, predictive motion planning with feedback control, and robustness to variability in human motion. Enabling such skills is of interest for advancing physical human-robot interaction and shared autonomy. We present a real-time planning and control architecture for human-robot partner juggling that enables a robot to reliably catch and throw balls in synchronized multi-ball patterns with a human partner. The system integrates predictive ball tracking, adaptive online trajectory optimization using a multiple-shooting formulation, and a state-machine-based coordination logic to enable synchronized multi-ball human-robot partner juggling. In a user study with 8 participants of varying juggling skill from beginner to expert, we demonstrate that our system can achieve three-ball cascades shared between the robot and the human. All participants exceeded previously reported best-case results within a 10-minute test session, with one participant extending the previous record for shared three-ball cascade juggling fivefold to 20 consecutive robot catches, and another participant achieving a 100% success rate with 40 consecutive catches in a single-ball catch-and-return setting. Video documentation can be found at https://kai-ploeger.com/partner-juggling

Other0 citations2026-07-16arXiv ->

KineFuse: Kinematic-Aware Haptic Fusion for In-Hand Occluded-Object Pose Tracking

Chanyoung Ahn, Jaesung Lee, Sungwoo Park, Donghyun Hwang

Dexterous in-hand manipulation requires continuous 6D pose tracking, yet the manipulating fingers inevitably occlude the object from the camera. We study how to structure the sparse haptic signals already available on multi-fingered hands, including proprioception, proximal force/torque, and binary contact, to complement a pretrained visual pose tracker under occlusion. We propose a kinematic-aware finger-level encoder and systematically compare it against four alternative designs through three levels of evaluation: per-frame refinement, sequential open-loop tracking, and closed-loop manipulation. Our experiments reveal that (i) per-frame evaluation cannot distinguish encoder quality, while sequential tracking amplifies architectural differences by up to 15 times; (ii) the structured encoder learns task-specific cross-modal gating, using vision exclusively for translation and dedicating one attention head to haptics for rotation, without explicit supervision; and (iii) compact finger-level tokenization with 4 tokens outperforms both flat fusion and joint-level representations, which suppress vision through norm dominance. We validate that improved tracking yields higher success in a downstream reorientation task and provide qualitative real-world demonstrations. Our project page is available at https://cold-young.github.io/kine-fuse/.

Robotics0 citations2026-07-16arXiv ->

BridgeFlow: Fast and Robust SE(2)-Equivariant Motion Planning with Flow Matching

Xinzhe Zhou, Xuyang Wang, Xiaoming Duan, Jianping He

In robotic motion planning, equivariance to rigid body transformations is crucial for robust spatial generalization. However, current learning-based planners face a critical dilemma: they either lack inherent equivariance, treating transformed tasks as novel scenarios, or enforce it via computationally expensive specialized architectures that bottleneck real-time inference. To break this trade-off, we propose BridgeFlow, a fast and strictly SE(2)-equivariant generative motion planning framework. Rather than relying on heavy equivariant networks, BridgeFlow achieves exact spatial equivariance via a lightweight task-centric canonicalization module, enabling generalization using standard architectures. To further accelerate inference, we pair a Brownian bridge informative prior with context-aware mini-batch optimal transport. This constructs a straightened vector field that minimizes transport costs and stabilizes training. Furthermore, environmental awareness is explicitly embedded via Classifier-Free Guidance. Evaluations in dense 2D environments and on a 7-DoF Franka manipulator demonstrate that BridgeFlow achieves up to a 15x inference speedup and a 2x higher valid trajectory rate over state-of-the-art diffusion baselines, alongside robust generalization to entirely unseen environments and arbitrary spatial transformations.

Robotics0 citations2026-07-16arXiv ->

Reinforcement Learning for the Full Strawberry Harvesting Process: Obstacle Separation, Detachment, and Placement

Changyou Miao, Teng Li, Ya Xiong

Severe occlusions and deformable plant structures introduce complex contact dynamics that challenge robotic strawberry harvesting. A policy-driven reinforcement learning (RL) framework with heuristic phase coordination was developed, in which obstacle separation, fruit detachment, and placement were formulated as a sequential decision-making task. A shared interaction-aware policy generated Cartesian motions across all task phases, while lightweight heuristic logic coordinated task progression and gripper events. A shared structured observation space was used to represent target, obstacle, end-effector, and task-context information. A hierarchical architecture combined the high-level policy with low-level Cartesian impedance control for compliant interaction. To support zero-shot sim-to-real transfer, feasibility-first observation alignment and domain randomization were adopted. The policy achieved success rates of 89.7% in simulation and 82.0% in real-world experiments. As the occlusion level increased from 1 to 5, the average execution time increased from 12.99 s to 21.73 s, reflecting greater interaction complexity. These results demonstrated effective transfer of interaction-aware harvesting behaviors to a structurally different robotic platform.

MPC/Planning0 citations2026-07-16arXiv ->

NavCMPO: Critic-Guided MeanFlow Policy Optimization for Adaptive Navigation

Junjie An, Yi Wu, Xiao Liu, Yiqun Zhou, Yuechen Wu et al.

End-to-end diffusion-based policies have demonstrated strong performance in mapless visual navigation, but their iterative denoising process introduces substantial inference latency, while behavior cloning limits performance to the quality of expert demonstrations. We present NavCMPO, a two-stage adaptive navigation framework that combines few-step MeanFlow trajectory generation, critic-guided refinement, and reinforcement learning fine-tuning. During pre-training, an obstacle proximity prediction task encourages the visual representation to capture obstacle-aware spatial information. To compensate for the degradation in obstacle avoidance caused by few-step generation, Critic-Guided Trajectory Refinement (CGTR) uses gradients from a critic trained with obstacle-point-cloud supervision to refine intermediate trajectories. During adaptation, the MeanFlow policy is fine-tuned using Proximal Policy Optimization with behavior-cloning regularization, while the critic is updated to accommodate embodiment-specific observation changes. Under a matched training budget on the InternVLA-N1 benchmark, NavCMPO achieves an average success rate of 74.7\%, exceeding the retrained NavDP baseline by 6.4 percentage points, while reducing inference latency from 85\,ms to 60\,ms. Experiments on a Unitree Go2 further demonstrate effective sim-to-real transfer.

Robotics0 citations2026-07-16arXiv ->

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation

Yi Wu, Junjie An, Xiao Liu, Yiqun Zhou, Yuechen Wu et al.

In goal-directed embodied navigation, where an agent must locate a specified target in an unseen environment, 3D scene understanding and navigation reasoning must work in concert. Current approaches transmit 3D scene information to vision-language models (VLMs) through text, suggesting a representation gap in our tested configurations; a controlled ablation confirms that direct embedding-level transfer significantly outperforms the evaluated text serialization formats. We introduce SoftNav, which injects entity-level 3D continuous representations -- one token per detected object or frontier -- into a VLM's hidden space as soft tokens through a lightweight projector. With the 3D encoder and VLM frozen, only ~1,200 samples and ~17M trainable parameters are needed. On HM3D-OVON, SoftNav achieves 74.2%/68.3%/66.7% SR across three splits, surpassing all prior methods in both SR and SPL; the same navigation policy transfers zero-shot to GOAT-Bench (67.2% SR), SG3D (47.2% s-SR), and real-world robot deployment without retraining or architectural modification. Injecting 3D scene tokens directly into VLMs bridges the representation gap, enabling transferable navigation with minimal training.

Learning0 citations2026-07-16arXiv ->

Beyond Implicit Force: Evaluating Explicit Force-Torque Proxies in Action Chunking with Transformers

King Hang Wong, Lingqiao Liu, Feras Dayoub

Contact-rich manipulation requires policies to infer interaction state from signals that are often weakly observable through vision and kinematics alone. Action Chunking with Transformers (ACT) has shown strong performance in fine-grained manipulation, but many deployments collect demonstrations through leader-follower teleoperation, where tracking error between commanded leader motion and executed follower motion implicitly encodes contact, resistance, and constraint violation. This paper examines whether ACT's apparent force-awareness depends on this hidden interaction cue. We introduce an observation-centric ACT variant that predicts future follower joint states instead of leader commands, thereby removing the teleoperation-induced discrepancy signal while preserving the rest of the learning pipeline. We then evaluate whether simple joint-torque proxies, derived from onboard motor current or joint effort, can recover contact-aware behavior without external force/torque sensors. Across four real-world tasks spanning surface following, insertion, stiffness discrimination, and force-based stopping, removing the implicit cue leads to severe failures in force-critical phases. In contrast, torque-augmented policies recover robust contact behavior and improve the base ACT policy. These results demonstrate that, on real hardware, the implicit teleoperation cue is a recoverable source of force-awareness, where torque signals are available, a simple proxy matches, surpasses, or further enhances it.

Robotics0 citations2026-07-16arXiv ->

Mixed-Agent Museum Tour Guide Design Improves Gendered Learning Outcomes and Visitor Preferences

Annette M. Masterson, Wonse Jo, Helena C. Sieh, Lionel P. Robert,, Dawn Tilbury

Robots are increasingly integrated into everyday contexts, including museums, where they can both entertain and educate visitors. To enhance visitor experience and engagement, we present a novel mixed-agent tour guide system that combines a physical robot with a projected virtual agent that actively participates in the tour through conversation and interaction, achieving the interaction richness of two mobile agents from a single platform. We validate the system through a within-subjects study with 30 participants to assess engagement, quality of experience, and learning performance. Participants experienced different conversational styles and agent configurations, and data were collected via surveys, behavioral sensors, and interviews. Results showed that engagement and quality of experience remained consistent across conditions. Learning performance revealed a significant gender-moderated difference: the mixed-agent conditions improved learning performance for female participants. This suggests that the proposed dyadic conversational style in this paper influenced learning performance differently by gender. Nonetheless, in interviews, participants reported a greater preference for mixed-agent teams regardless of gender, citing interaction as a key factor in their experience.

IROS 2025 | 41 papers
CBF Related Papers
Robotics0 citations2025-10-01arXiv ->

Safe Motion Planning and Control Using Predictive and Adaptive Barrier Methods for Autonomous Surface Vessels

Alejandro Gonzalez-Garcia, Wei Xiao, Wei Wang, Alejandro Astudillo, Wilm Decré et al.

Safe motion planning is essential for autonomous vessel operations, especially in challenging spaces such as narrow inland waterways. However, conventional motion planning approaches are often computationally intensive or overly conservative. This paper proposes a safe motion planning strategy combining Model Predictive Control (MPC) and Control Barrier Functions (CBFs). We introduce a time-varying inflated ellipse obstacle representation, where the inflation radius is adjusted depending on the relative position and attitude between the vessel and the obstacle. The proposed adaptive inflation reduces the conservativeness of the controller compared to traditional fixed-ellipsoid obstacle formulations. The MPC solution provides an approximate motion plan, and high-order CBFs ensure the vessel's safety using the varying inflation radius. Simulation and real-world experiments demonstrate that the proposed strategy enables the fully-actuated autonomous robot vessel to navigate through narrow spaces in real time and resolve potential deadlocks, all while ensuring safety.

Other Papers
Robotics0 citations2026-07-20arXiv ->

CDIS: Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging

Juno Kim, Hye-Jung Yoon, Yesol Park, Byoung-Tak Zhang

Class-agnostic 3D instance segmentation is critical for robotic systems operating in unknown environments, enabling perception of previously unseen objects for reliable manipulation and navigation. Existing approaches typically project per-frame 2D instance masks into 3D and merge them, which often breaks object identities across time and yields fragmented 3D instances. We introduce Cross-Dimensional Class-Agnostic 3D Instance Segmentation (CDIS), a zero-shot framework that explicitly tracks 2D instance masks across frames and associates them with 3D superpoints, creating a feedback loop between 2D and 3D. This cross-dimensional reasoning links temporally stable 2D tracks with spatially coherent 3D regions, producing globally consistent 3D instance labels without any 3D-specific training. Experiments on benchmark datasets demonstrate that CDIS achieves higher accuracy and consistency than state-of-the-art zero-shot methods, while remaining efficient and scalable to diverse real-world environments.

Robotics0 citations2026-06-30arXiv ->

LLM-Powered Interactive Robotic Action Synthesis from Multimodal Speech, Gestures, and Music

Snehasis Banerjee, Ranjan Dasgupta

The quest for intuitive and natural human-robot interaction (HRI) remains a significant challenge in robotics. Traditional methods often rely on rigid, pre-programmed commands that limit the robot's expressiveness and adaptability. This paper introduces a novel framework that leverages the reasoning capabilities of Large Language Models (LLMs) to synthesize complex robotic actions from a rich tapestry of multimodal human inputs: natural speech, hand gestures, and music/sound beats. Our system architecture integrates a speech transcription model, a gesture recognition module, and a signal processing pipeline for beat detection. These processed inputs are contextualized using prompt templates and fed into a LLM. The LLM, informed by a predefined robot action space, reasons over the combined inputs to generate a coherent sequence of actions. This sequence is dispatched to an action queue for execution on a quadruped robot over ROS. The framework has ability to interpret and fuse semantic commands from speech, deictic information from gestures, and rhythmic cues from music. This work represents a step towards creating robots that can interact with humans in a more fluid, creative, and context-aware manner.

Robotics0 citations2026-06-30arXiv ->

A Modular Vision-Language-Action Robotics Framework for Indoor Environments

Anindya Jana, Snehasis Banerjee, Arup Sadhu, Ranjan Dasgupta

This paper presents an integrated system for the CMU Vision-Language-Action (VLA) Challenge, designed to enable an autonomous agent to perform complex tasks based on natural language instructions. Our framework employs a modular architecture that orchestrates environment mapping, question processing, and navigation. The system operates in two parallel streams: a perception pipeline that constructs a semantic voxel map from real-time camera feeds using OwlViT embeddings, and a language pipeline that classifies user commands with a Vision-Language Model. The mapping is time-constrained; the system proceeds with a partial map if a 500-second exploration limit is reached. The classified query is then grounded in the geometric and semantic context of the map to generate a detailed prompt for the VLM. This yields an actionable output, demonstrating a capable solution for bridging the gap between human language and robotic action.

MPC/Planning0 citations2026-04-18arXiv ->

NaviFormer: A Deep Reinforcement Learning Transformer-like Model to Holistically Solve the Navigation Problem

Daniel Fuertes, Andrea Cavallaro, Carlos R. del-Blanco, Fernando Jaureguizar, Narciso García

Path planning is usually solved by addressing either the (high-level) route planning problem (waypoint sequencing to achieve the final goal) or the (low-level) path planning problem (trajectory prediction between two waypoints avoiding collisions). However, real-world problems usually require simultaneous solutions to the route and path planning subproblems with a holistic and efficient approach. In this paper, we introduce NaviFormer, a deep reinforcement learning model based on a Transformer architecture that solves the global navigation problem by predicting both high-level routes and low-level trajectories. To evaluate NaviFormer, several experiments have been conducted, including comparisons with other algorithms. Results show competitive accuracy from NaviFormer since it can understand the constraints and difficulties of each subproblem and act consequently to improve performance. Moreover, its superior computation speed proves its suitability for real-time missions.

Robotics0 citations2026-03-04arXiv ->

GIANT - Global Path Integration and Attentive Graph Networks for Multi-Agent Trajectory Planning

Jonas le Fevre Sejersen, Toyotaro Suzumura, Erdal Kayacan

This paper presents a novel approach to multi-robot collision avoidance that integrates global path planning with local navigation strategies, utilizing attentive graph neural networks to manage dynamic interactions among agents. We introduce a local navigation model that leverages pre-planned global paths, allowing robots to adhere to optimal routes while dynamically adjusting to environmental changes. The models robustness is enhanced through the introduction of noise during training, resulting in superior performance in complex, dynamic environments. Our approach is evaluated against established baselines, including NH-ORCA, DRL-NAV, and GA3C-CADRL, across various structurally diverse simulated scenarios. The results demonstrate that our model achieves consistently higher success rates, lower collision rates, and more efficient navigation, particularly in challenging scenarios where baseline models struggle. This work offers an advancement in multi-robot navigation, with implications for robust performance in complex, dynamic environments with varying degrees of complexity, such as those encountered in logistics, where adaptability is essential for accommodating unforeseen obstacles and unpredictable changes.

Robotics0 citations2026-01-29arXiv ->

Thinker: A vision-language foundation model for embodied intelligence

Baiyu Pan, Daqin Luo, Junpeng Yang, Jiyuan Wang, Yixuan Zhang et al.

When large vision-language models are applied to the field of robotics, they encounter problems that are simple for humans yet error-prone for models. Such issues include confusion between third-person and first-person perspectives and a tendency to overlook information in video endings during temporal reasoning. To address these challenges, we propose Thinker, a large vision-language foundation model designed for embodied intelligence. We tackle the aforementioned issues from two perspectives. Firstly, we construct a large-scale dataset tailored for robotic perception and reasoning, encompassing ego-view videos, visual grounding, spatial understanding, and chain-of-thought data. Secondly, we introduce a simple yet effective approach that substantially enhances the model's capacity for video comprehension by jointly incorporating key frames and full video sequences as inputs. Our model achieves state-of-the-art results on two of the most commonly used benchmark datasets in the field of task planning.

Robotics0 citations2026-01-08arXiv ->

The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms

Lingdong Kong, Shaoyuan Xie, Zeying Gong, Ye Li, Meng Chu et al.

Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under sensor noise, environmental variation, and platform shifts. However, even state-of-the-art methods often degrade under unseen conditions, highlighting the need for robust and generalizable robot sensing. The RoboSense 2025 Challenge is designed to advance robustness and adaptability in robot perception across diverse sensing scenarios. It unifies five complementary research tracks spanning language-grounded decision making, socially compliant navigation, sensor configuration generalization, cross-view and cross-modal correspondence, and cross-platform 3D perception. Together, these tasks form a comprehensive benchmark for evaluating real-world sensing reliability under domain shifts, sensor failures, and platform discrepancies. RoboSense 2025 provides standardized datasets, baseline models, and unified evaluation protocols, enabling large-scale and reproducible comparison of robust perception methods. The challenge attracted 143 teams from 85 institutions across 16 countries, reflecting broad community engagement. By consolidating insights from 23 winning solutions, this report highlights emerging methodological trends, shared design principles, and open challenges across all tracks, marking a step toward building robots that can sense reliably, act robustly, and adapt across platforms in real-world environments.

Robotics0 citations2026-01-01arXiv ->

Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers

Söhnke Benedikt Fischedick, Daniel Seichter, Benedict Stephan, Robin Schmidt, Horst-Michael Gross

In domestic environments, robots require a comprehensive understanding of their surroundings to interact effectively and intuitively with untrained humans. In this paper, we propose DVEFormer - an efficient RGB-D Transformer-based approach that predicts dense text-aligned visual embeddings (DVE) via knowledge distillation. Instead of directly performing classical semantic segmentation with fixed predefined classes, our method uses teacher embeddings from Alpha-CLIP to guide our efficient student model DVEFormer in learning fine-grained pixel-wise embeddings. While this approach still enables classical semantic segmentation, e.g., via linear probing, it further enables flexible text-based querying and other applications, such as creating comprehensive 3D maps. Evaluations on common indoor datasets demonstrate that our approach achieves competitive performance while meeting real-time requirements, operating at 26.3 FPS for the full model and 77.0 FPS for a smaller variant on an NVIDIA Jetson AGX Orin. Additionally, we show qualitative results that highlight the effectiveness and possible use cases in real-world applications. Overall, our method serves as a drop-in replacement for traditional segmentation approaches while enabling flexible natural-language querying and seamless integration into 3D mapping pipelines for mobile robotics.

Robotics0 citations2025-12-30arXiv ->

Local Path Optimization in The Latent Space Using Learned Distance Gradient

Jiawei Zhang, Chengchao Bai, Wei Pan, Tianhang Liu, Jifeng Guo

Constrained motion planning is a common but challenging problem in robotic manipulation. In recent years, data-driven constrained motion planning algorithms have shown impressive planning speed and success rate. Among them, the latent motion method based on manifold approximation is the most efficient planning algorithm. Due to errors in manifold approximation and the difficulty in accurately identifying collision conflicts within the latent space, time-consuming path validity checks and path replanning are required. In this paper, we propose a method that trains a neural network to predict the minimum distance between the robot and obstacles using latent vectors as inputs. The learned distance gradient is then used to calculate the direction of movement in the latent space to move the robot away from obstacles. Based on this, a local path optimization algorithm in the latent space is proposed, and it is integrated with the path validity checking process to reduce the time of replanning. The proposed method is compared with state-of-the-art algorithms in multiple planning scenarios, demonstrating the fastest planning speed

MPC/Planning0 citations2025-12-30arXiv ->

Heteroscedastic Bayesian Optimization-Based Dynamic PID Tuning for Accurate and Robust UAV Trajectory Tracking

Fuqiang Gu, Jiangshan Ai, Xu Lu, Xianlei Long, Yan Li et al.

Unmanned Aerial Vehicles (UAVs) play an important role in various applications, where precise trajectory tracking is crucial. However, conventional control algorithms for trajectory tracking often exhibit limited performance due to the underactuated, nonlinear, and highly coupled dynamics of quadrotor systems. To address these challenges, we propose HBO-PID, a novel control algorithm that integrates the Heteroscedastic Bayesian Optimization (HBO) framework with the classical PID controller to achieve accurate and robust trajectory tracking. By explicitly modeling input-dependent noise variance, the proposed method can better adapt to dynamic and complex environments, and therefore improve the accuracy and robustness of trajectory tracking. To accelerate the convergence of optimization, we adopt a two-stage optimization strategy that allow us to more efficiently find the optimal controller parameters. Through experiments in both simulation and real-world scenarios, we demonstrate that the proposed method significantly outperforms state-of-the-art (SOTA) methods. Compared to SOTA methods, it improves the position accuracy by 24.7% to 42.9%, and the angular accuracy by 40.9% to 78.4%.

Robotics0 citations2025-12-24arXiv ->

Stretchable and High-Precision Optical Tactile Sensor for Trajectory Tracking of Parallel Mechanisms

Yiding Nie, Dongliang Fan, Jiatai Huang, Chunyu Liu, Jian S. Dai

Stretchable sensors indicate promising prospects for soft robotics, medical devices, and human-machine interactions due to the high compliance of soft materials. Discrete sensing strategies, including sensor arrays and distributed sensors, are broadly involved in tactile sensors across versatile applications. However, it remains a challenge to achieve high spatial resolution with self-decoupled capacity and insensitivity to other off-axis stimuli for stretchable tactile sensors. Herein, we develop a stretchable tactile sensor based on the proposed continuous spectral-filtering principle, allowing superhigh resolution for applied stimuli. This proposed sensor enables a high-linear spatial response (0.996) even during stretching and bending, and high continuous spatial (7 μm) and force (5 mN) resolutions with design scalability and interaction robustness to survive piercing and cutting. We further demonstrate the sensors' performance by integrating them into a planar parallel mechanism for precise trajectory tracking (rotational resolution: 0.02°) in real time.

Robotics0 citations2025-12-23arXiv ->

Energy-Efficient Omnidirectional Locomotion for Wheeled Quadrupeds via Predictive Energy-Aware Nominal Gait Selection

Xu Yang, Wei Yang, Kaibo He, Bo Yang, Yanan Sui et al.

Wheeled-legged robots combine the efficiency of wheels with the versatility of legs, but face significant energy optimization challenges when navigating diverse environments. In this work, we present a hierarchical control framework that integrates predictive power modeling with residual reinforcement learning to optimize omnidirectional locomotion efficiency for wheeled quadrupedal robots. Our approach employs a novel power prediction network that forecasts energy consumption across different gait patterns over a 1-second horizon, enabling intelligent selection of the most energy-efficient nominal gait. A reinforcement learning policy then generates residual adjustments to this nominal gait, fine-tuning the robot's actions to balance energy efficiency with performance objectives. Comparative analysis shows our method reduces energy consumption by up to 35\% compared to fixed-gait approaches while maintaining comparable velocity tracking performance. We validate our framework through extensive simulations and real-world experiments on a modified Unitree Go1 platform, demonstrating robust performance even under external disturbances. Videos and implementation details are available at \href{https://sites.google.com/view/switching-wpg}{https://sites.google.com/view/switching-wpg}.

Robotics0 citations2025-12-19arXiv ->

SurgiPose: Estimating Surgical Tool Kinematics from Monocular Video for Surgical Robot Learning

Juo-Tung Chen, XinHao Chen, Ji Woong Kim, Paul Maria Scheikl, Richard Jaepyeong Cha et al.

Imitation learning (IL) has shown immense promise in enabling autonomous dexterous manipulation, including learning surgical tasks. To fully unlock the potential of IL for surgery, access to clinical datasets is needed, which unfortunately lack the kinematic data required for current IL approaches. A promising source of large-scale surgical demonstrations is monocular surgical videos available online, making monocular pose estimation a crucial step toward enabling large-scale robot learning. Toward this end, we propose SurgiPose, a differentiable rendering based approach to estimate kinematic information from monocular surgical videos, eliminating the need for direct access to ground truth kinematics. Our method infers tool trajectories and joint angles by optimizing tool pose parameters to minimize the discrepancy between rendered and real images. To evaluate the effectiveness of our approach, we conduct experiments on two robotic surgical tasks: tissue lifting and needle pickup, using the da Vinci Research Kit Si (dVRK Si). We train imitation learning policies with both ground truth measured kinematics and estimated kinematics from video and compare their performance. Our results show that policies trained on estimated kinematics achieve comparable success rates to those trained on ground truth data, demonstrating the feasibility of using monocular video based kinematic estimation for surgical robot learning. By enabling kinematic estimation from monocular surgical videos, our work lays the foundation for large scale learning of autonomous surgical policies from online surgical data.

Learning0 citations2025-12-16arXiv ->

CLAIM: Camera-LiDAR Alignment with Intensity and Monodepth

Zhuo Zhang, Yonghui Liu, Meijie Zhang, Feiyang Tan, Yikang Ding

In this paper, we unleash the potential of the powerful monodepth model in camera-LiDAR calibration and propose CLAIM, a novel method of aligning data from the camera and LiDAR. Given the initial guess and pairs of images and LiDAR point clouds, CLAIM utilizes a coarse-to-fine searching method to find the optimal transformation minimizing a patched Pearson correlation-based structure loss and a mutual information-based texture loss. These two losses serve as good metrics for camera-LiDAR alignment results and require no complicated steps of data processing, feature extraction, or feature matching like most methods, rendering our method simple and adaptive to most scenes. We validate CLAIM on public KITTI, Waymo, and MIAS-LCEC datasets, and the experimental results demonstrate its superior performance compared with the state-of-the-art methods. The code is available at https://github.com/Tompson11/claim.

Robotics0 citations2025-12-11arXiv ->

Mr. Virgil: Learning Multi-robot Visual-range Relative Localization

Si Wang, Zhehan Li, Jiadong Lu, Rong Xiong, Yanjun Cao et al.

Ultra-wideband (UWB)-vision fusion localization has achieved extensive applications in the domain of multi-agent relative localization. The challenging matching problem between robots and visual detection renders existing methods highly dependent on identity-encoded hardware or delicate tuning algorithms. Overconfident yet erroneous matches may bring about irreversible damage to the localization system. To address this issue, we introduce Mr. Virgil, an end-to-end learning multi-robot visual-range relative localization framework, consisting of a graph neural network for data association between UWB rangings and visual detections, and a differentiable pose graph optimization (PGO) back-end. The graph-based front-end supplies robust matching results, accurate initial position predictions, and credible uncertainty estimates, which are subsequently integrated into the PGO back-end to elevate the accuracy of the final pose estimation. Additionally, a decentralized system is implemented for real-world applications. Experiments spanning varying robot numbers, simulation and real-world, occlusion and non-occlusion conditions showcase the stability and exactitude under various scenes compared to conventional methods. Our code is available at: https://github.com/HiOnes/Mr-Virgil.

Robotics0 citations2025-11-19arXiv ->

Decentralized Gaussian Process Classification and an Application in Subsea Robotics

Yifei Gao, Hans J. He, Daniel J. Stilwell, James McMahon

Teams of cooperating autonomous underwater vehicles (AUVs) rely on acoustic communication for coordination, yet this communication medium is constrained by limited range, multi-path effects, and low bandwidth. One way to address the uncertainty associated with acoustic communication is to learn the communication environment in real-time. We address the challenge of a team of robots building a map of the probability of communication success from one location to another in real-time. This is a decentralized classification problem -- communication events are either successful or unsuccessful -- where AUVs share a subset of their communication measurements to build the map. The main contribution of this work is a rigorously derived data sharing policy that selects measurements to be shared among AUVs. We experimentally validate our proposed sharing policy using real acoustic communication data collected from teams of Virginia Tech 690 AUVs, demonstrating its effectiveness in underwater environments.

Robotics0 citations2025-11-19arXiv ->

RRT*former: Environment-Aware Sampling-Based Motion Planning using Transformer

Mingyang Feng, Shaoyuan Li, Xiang Yin

We investigate the sampling-based optimal path planning problem for robotics in complex and dynamic environments. Most existing sampling-based algorithms neglect environmental information or the information from previous samples. Yet, these pieces of information are highly informative, as leveraging them can provide better heuristics when sampling the next state. In this paper, we propose a novel sampling-based planning algorithm, called \emph{RRT*former}, which integrates the standard RRT* algorithm with a Transformer network in a novel way. Specifically, the Transformer is used to extract features from the environment and leverage information from previous samples to better guide the sampling process. Our extensive experiments demonstrate that, compared to existing sampling-based approaches such as RRT*, Neural RRT*, and their variants, our algorithm achieves considerable improvements in both the optimality of the path and sampling efficiency. The code for our implementation is available on https://github.com/fengmingyang666/RRTformer.

Robotics0 citations2025-11-18arXiv ->

iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversion

Hao Wang, Linqing Zhao, Xiuwei Xu, Jiwen Lu, Haibin Yan

Recent trends in SLAM and visual navigation have embraced 3D Gaussians as the preferred scene representation, highlighting the importance of estimating camera poses from a single image using a pre-built Gaussian model. However, existing approaches typically rely on an iterative \textit{render-compare-refine} loop, where candidate views are first rendered using NeRF or Gaussian Splatting, then compared against the target image, and finally, discrepancies are used to update the pose. This multi-round process incurs significant computational overhead, hindering real-time performance in robotics. In this paper, we propose iGaussian, a two-stage feed-forward framework that achieves real-time camera pose estimation through direct 3D Gaussian inversion. Our method first regresses a coarse 6DoF pose using a Gaussian Scene Prior-based Pose Regression Network with spatial uniform sampling and guided attention mechanisms, then refines it through feature matching and multi-model fusion. The key contribution lies in our cross-correlation module that aligns image embeddings with 3D Gaussian attributes without differentiable rendering, coupled with a Weighted Multiview Predictor that fuses features from Multiple strategically sampled viewpoints. Experimental results on the NeRF Synthetic, Mip-NeRF 360, and T\&T+DB datasets demonstrate a significant performance improvement over previous methods, reducing median rotation errors to 0.2° while achieving 2.87 FPS tracking on mobile robots, which is an impressive 10 times speedup compared to optimization-based approaches. Code: https://github.com/pythongod-exe/iGaussian

Robotics0 citations2025-11-17arXiv ->

OpenRoboCare: A Multimodal Multi-Task Expert Demonstration Dataset for Robot Caregiving

Xiaoyu Liang, Ziang Liu, Kelvin Lin, Edward Gu, Ruolin Ye et al.

We present OpenRoboCare, a multimodal dataset for robot caregiving, capturing expert occupational therapist demonstrations of Activities of Daily Living (ADLs). Caregiving tasks involve complex physical human-robot interactions, requiring precise perception under occlusions, safe physical contact, and long-horizon planning. While recent advances in robot learning from demonstrations have shown promise, there is a lack of a large-scale, diverse, and expert-driven dataset that captures real-world caregiving routines. To address this gap, we collect data from 21 occupational therapists performing 15 ADL tasks on two manikins. The dataset spans five modalities: RGB-D video, pose tracking, eye-gaze tracking, task and action annotations, and tactile sensing, providing rich multimodal insights into caregiver movement, attention, force application, and task execution strategies. We further analyze expert caregiving principles and strategies, offering insights to improve robot efficiency and task feasibility. Additionally, our evaluations demonstrate that OpenRoboCare presents challenges for state-of-the-art robot perception and human activity recognition methods, both critical for developing safe and adaptive assistive robots, highlighting the value of our contribution. See our website for additional visualizations: https://emprise.cs.cornell.edu/robo-care/.

Robotics0 citations2025-11-17arXiv ->

TOPP-DWR: Time-Optimal Path Parameterization of Differential-Driven Wheeled Robots Considering Piecewise-Constant Angular Velocity Constraints

Yong Li, Yujun Huang, Yi Chen, Hui Cheng

Differential-driven wheeled robots (DWR) represent the quintessential type of mobile robots and find extensive appli- cations across the robotic field. Most high-performance control approaches for DWR explicitly utilize the linear and angular velocities of the trajectory as control references. However, existing research on time-optimal path parameterization (TOPP) for mobile robots usually neglects the angular velocity and joint vel- ocity constraints, which can result in degraded control perfor- mance in practical applications. In this article, a systematic and practical TOPP algorithm named TOPP-DWR is proposed for DWR and other mobile robots. First, the non-uniform B-spline is adopted to represent the initial trajectory in the task space. Second, the piecewise-constant angular velocity, as well as joint velocity, linear velocity, and linear acceleration constraints, are incorporated into the TOPP problem. During the construction of the optimization problem, the aforementioned constraints are uniformly represented as linear velocity constraints. To boost the numerical computational efficiency, we introduce a slack variable to reformulate the problem into second-order-cone programming (SOCP). Subsequently, comparative experiments are conducted to validate the superiority of the proposed method. Quantitative performance indexes show that TOPP-DWR achieves TOPP while adhering to all constraints. Finally, field autonomous navigation experiments are carried out to validate the practicability of TOPP-DWR in real-world applications.

MPC/Planning0 citations2025-11-12arXiv ->

Diffusion Policies with Value-Conditional Optimization for Offline Reinforcement Learning

Yunchang Ma, Tenglong Liu, Yixing Lan, Xin Yin, Changxin Zhang et al.

In offline reinforcement learning, value overestimation caused by out-of-distribution (OOD) actions significantly limits policy performance. Recently, diffusion models have been leveraged for their strong distribution-matching capabilities, enforcing conservatism through behavior policy constraints. However, existing methods often apply indiscriminate regularization to redundant actions in low-quality datasets, resulting in excessive conservatism and an imbalance between the expressiveness and efficiency of diffusion modeling. To address these issues, we propose DIffusion policies with Value-conditional Optimization (DIVO), a novel approach that leverages diffusion models to generate high-quality, broadly covered in-distribution state-action samples while facilitating efficient policy improvement. Specifically, DIVO introduces a binary-weighted mechanism that utilizes the advantage values of actions in the offline dataset to guide diffusion model training. This enables a more precise alignment with the dataset's distribution while selectively expanding the boundaries of high-advantage actions. During policy improvement, DIVO dynamically filters high-return-potential actions from the diffusion model, effectively guiding the learned policy toward better performance. This approach achieves a critical balance between conservatism and explorability in offline RL. We evaluate DIVO on the D4RL benchmark and compare it against state-of-the-art baselines. Empirical results demonstrate that DIVO achieves superior performance, delivering significant improvements in average returns across locomotion tasks and outperforming existing methods in the challenging AntMaze domain, where sparse rewards pose a major difficulty.

Robotics0 citations2025-11-10arXiv ->

Leveraging Text-Driven Semantic Variation for Robust OOD Segmentation

Seungheon Song, Jaekoo Lee

In autonomous driving and robotics, ensuring road safety and reliable decision-making critically depends on out-of-distribution (OOD) segmentation. While numerous methods have been proposed to detect anomalous objects on the road, leveraging the vision-language space-which provides rich linguistic knowledge-remains an underexplored field. We hypothesize that incorporating these linguistic cues can be especially beneficial in the complex contexts found in real-world autonomous driving scenarios. To this end, we present a novel approach that trains a Text-Driven OOD Segmentation model to learn a semantically diverse set of objects in the vision-language space. Concretely, our approach combines a vision-language model's encoder with a transformer decoder, employs Distance-Based OOD prompts located at varying semantic distances from in-distribution (ID) classes, and utilizes OOD Semantic Augmentation for OOD representations. By aligning visual and textual information, our approach effectively generalizes to unseen objects and provides robust OOD segmentation in diverse driving environments. We conduct extensive experiments on publicly available OOD segmentation datasets such as Fishyscapes, Segment-Me-If-You-Can, and Road Anomaly datasets, demonstrating that our approach achieves state-of-the-art performance across both pixel-level and object-level evaluations. This result underscores the potential of vision-language-based OOD segmentation to bolster the safety and reliability of future autonomous driving systems.

Robotics0 citations2025-11-10arXiv ->

Semi-distributed Cross-modal Air-Ground Relative Localization

Weining Lu, Deer Bin, Lian Ma, Ming Ma, Zhihao Ma et al.

Efficient, accurate, and flexible relative localization is crucial in air-ground collaborative tasks. However, current approaches for robot relative localization are primarily realized in the form of distributed multi-robot SLAM systems with the same sensor configuration, which are tightly coupled with the state estimation of all robots, limiting both flexibility and accuracy. To this end, we fully leverage the high capacity of Unmanned Ground Vehicle (UGV) to integrate multiple sensors, enabling a semi-distributed cross-modal air-ground relative localization framework. In this work, both the UGV and the Unmanned Aerial Vehicle (UAV) independently perform SLAM while extracting deep learning-based keypoints and global descriptors, which decouples the relative localization from the state estimation of all agents. The UGV employs a local Bundle Adjustment (BA) with LiDAR, camera, and an IMU to rapidly obtain accurate relative pose estimates. The BA process adopts sparse keypoint optimization and is divided into two stages: First, optimizing camera poses interpolated from LiDAR-Inertial Odometry (LIO), followed by estimating the relative camera poses between the UGV and UAV. Additionally, we implement an incremental loop closure detection algorithm using deep learning-based descriptors to maintain and retrieve keyframes efficiently. Experimental results demonstrate that our method achieves outstanding performance in both accuracy and efficiency. Unlike traditional multi-robot SLAM approaches that transmit images or point clouds, our method only transmits keypoint pixels and their descriptors, effectively constraining the communication bandwidth under 0.3 Mbps. Codes and data will be publicly available on https://github.com/Ascbpiac/cross-model-relative-localization.git.

Robotics0 citations2025-11-07arXiv ->

Let Me Show You: Learning by Retrieving from Egocentric Video for Robotic Manipulation

Yichen Zhu, Feifei Feng

Robots operating in complex and uncertain environments face considerable challenges. Advanced robotic systems often rely on extensive datasets to learn manipulation tasks. In contrast, when humans are faced with unfamiliar tasks, such as assembling a chair, a common approach is to learn by watching video demonstrations. In this paper, we propose a novel method for learning robot policies by Retrieving-from-Video (RfV), using analogies from human demonstrations to address manipulation tasks. Our system constructs a video bank comprising recordings of humans performing diverse daily tasks. To enrich the knowledge from these videos, we extract mid-level information, such as object affordance masks and hand motion trajectories, which serve as additional inputs to enhance the robot model's learning and generalization capabilities. We further feature a dual-component system: a video retriever that taps into an external video bank to fetch task-relevant video based on task specification, and a policy generator that integrates this retrieved knowledge into the learning cycle. This approach enables robots to craft adaptive responses to various scenarios and generalize to tasks beyond those in the training data. Through rigorous testing in multiple simulated and real-world settings, our system demonstrates a marked improvement in performance over conventional robotic systems, showcasing a significant breakthrough in the field of robotics.

Learning0 citations2025-11-06arXiv ->

BoRe-Depth: Self-supervised Monocular Depth Estimation with Boundary Refinement for Embedded Systems

Chang Liu, Juan Li, Sheng Zhang, Chang Liu, Jie Li et al.

Depth estimation is one of the key technologies for realizing 3D perception in unmanned systems. Monocular depth estimation has been widely researched because of its low-cost advantage, but the existing methods face the challenges of poor depth estimation performance and blurred object boundaries on embedded systems. In this paper, we propose a novel monocular depth estimation model, BoRe-Depth, which contains only 8.7M parameters. It can accurately estimate depth maps on embedded systems and significantly improves boundary quality. Firstly, we design an Enhanced Feature Adaptive Fusion Module (EFAF) which adaptively fuses depth features to enhance boundary detail representation. Secondly, we integrate semantic knowledge into the encoder to improve the object recognition and boundary perception capabilities. Finally, BoRe-Depth is deployed on NVIDIA Jetson Orin, and runs efficiently at 50.7 FPS. We demonstrate that the proposed model significantly outperforms previous lightweight models on multiple challenging datasets, and we provide detailed ablation studies for the proposed methods. The code is available at https://github.com/liangxiansheng093/BoRe-Depth.

Robotics0 citations2025-11-06arXiv ->

Integrating Ergonomics and Manipulability for Upper Limb Postural Optimization in Bimanual Human-Robot Collaboration

Chenzui Li, Yiming Chen, Xi Wu, Giacinto Barresi, Fei Chen

This paper introduces an upper limb postural optimization method for enhancing physical ergonomics and force manipulability during bimanual human-robot co-carrying tasks. Existing research typically emphasizes human safety or manipulative efficiency, whereas our proposed method uniquely integrates both aspects to strengthen collaboration across diverse conditions (e.g., different grasping postures of humans, and different shapes of objects). Specifically, the joint angles of a simplified human skeleton model are optimized by minimizing the cost function to prioritize safety and manipulative capability. To guide humans towards the optimized posture, the reference end-effector poses of the robot are generated through a transformation module. A bimanual model predictive impedance controller (MPIC) is proposed for our human-like robot, CURI, to recalibrate the end effector poses through planned trajectories. The proposed method has been validated through various subjects and objects during human-human collaboration (HHC) and human-robot collaboration (HRC). The experimental results demonstrate significant improvement in muscle conditions by comparing the activation of target muscles before and after optimization.

Robotics0 citations2025-11-03arXiv ->

FoldPath: End-to-End Object-Centric Motion Generation via Modulated Implicit Paths

Paolo Rabino, Gabriele Tiboni, Tatiana Tommasi

Object-Centric Motion Generation (OCMG) is instrumental in advancing automated manufacturing processes, particularly in domains requiring high-precision expert robotic motions, such as spray painting and welding. To realize effective automation, robust algorithms are essential for generating extended, object-aware trajectories across intricate 3D geometries. However, contemporary OCMG techniques are either based on ad-hoc heuristics or employ learning-based pipelines that are still reliant on sensitive post-processing steps to generate executable paths. We introduce FoldPath, a novel, end-to-end, neural field based method for OCMG. Unlike prior deep learning approaches that predict discrete sequences of end-effector waypoints, FoldPath learns the robot motion as a continuous function, thus implicitly encoding smooth output paths. This paradigm shift eliminates the need for brittle post-processing steps that concatenate and order the predicted discrete waypoints. Particularly, our approach demonstrates superior predictive performance compared to recently proposed learning-based methods, and attains generalization capabilities even in real industrial settings, where only a limited amount of 70 expert samples are provided. We validate FoldPath through comprehensive experiments in a realistic simulation environment and introduce new, rigorous metrics designed to comprehensively evaluate long-horizon robotic paths, thus advancing the OCMG task towards practical maturity.

Robotics0 citations2025-11-03arXiv ->

CM-LIUW-Odometry: Robust and High-Precision LiDAR-Inertial-UWB-Wheel Odometry for Extreme Degradation Coal Mine Tunnels

Kun Hu, Menggang Li, Zhiwen Jin, Chaoquan Tang, Eryi Hu et al.

Simultaneous Localization and Mapping (SLAM) in large-scale, complex, and GPS-denied underground coal mine environments presents significant challenges. Sensors must contend with abnormal operating conditions: GPS unavailability impedes scene reconstruction and absolute geographic referencing, uneven or slippery terrain degrades wheel odometer accuracy, and long, feature-poor tunnels reduce LiDAR effectiveness. To address these issues, we propose CoalMine-LiDAR-IMU-UWB-Wheel-Odometry (CM-LIUW-Odometry), a multimodal SLAM framework based on the Iterated Error-State Kalman Filter (IESKF). First, LiDAR-inertial odometry is tightly fused with UWB absolute positioning constraints to align the SLAM system with a global coordinate. Next, wheel odometer is integrated through tight coupling, enhanced by nonholonomic constraints (NHC) and vehicle lever arm compensation, to address performance degradation in areas beyond UWB measurement range. Finally, an adaptive motion mode switching mechanism dynamically adjusts the robot's motion mode based on UWB measurement range and environmental degradation levels. Experimental results validate that our method achieves superior accuracy and robustness in real-world underground coal mine scenarios, outperforming state-of-the-art approaches. We open source our code of this work on Github to benefit the robotics community.

Robotics0 citations2025-10-30arXiv ->

REALMS2 -- Resilient Exploration And Lunar Mapping System 2 -- A Comprehensive Approach

Dave van der Meer, Loïck P. Chovet, Gabriel M. Garcia, Abhishek Bera, Miguel A. Olivares-Mendez

The European Space Agency (ESA) and the European Space Resources Innovation Centre (ESRIC) created the Space Resources Challenge to invite researchers and companies to propose innovative solutions for Multi-Robot Systems (MRS) space prospection. This paper proposes the Resilient Exploration And Lunar Mapping System 2 (REALMS2), a MRS framework for planetary prospection and mapping. Based on Robot Operating System version 2 (ROS 2) and enhanced with Visual Simultaneous Localisation And Mapping (vSLAM) for map generation, REALMS2 uses a mesh network for a robust ad hoc network. A single graphical user interface (GUI) controls all the rovers, providing a simple overview of the robotic mission. This system is designed for heterogeneous multi-robot exploratory missions, tackling the challenges presented by extraterrestrial environments. REALMS2 was used during the second field test of the ESA-ESRIC Challenge and allowed to map around 60% of the area, using three homogeneous rovers while handling communication delays and blackouts.

Robotics0 citations2025-10-29arXiv ->

Efficient Online Learning with Predictive Coding Networks: Exploiting Temporal Correlations

Darius Masoum Zadeh-Jousdani, Elvin Hajizada, Eyke Hüllermeier

Robotic systems operating at the edge require efficient online learning algorithms that can continuously adapt to changing environments while processing streaming sensory data. Traditional backpropagation, while effective, conflicts with biological plausibility principles and may be suboptimal for continuous adaptation scenarios. The Predictive Coding (PC) framework offers a biologically plausible alternative with local, Hebbian-like update rules, making it suitable for neuromorphic hardware implementation. However, PC's main limitation is its computational overhead due to multiple inference iterations during training. We present Predictive Coding Network with Temporal Amortization (PCN-TA), which preserves latent states across temporal frames. By leveraging temporal correlations, PCN-TA significantly reduces computational demands while maintaining learning performance. Our experiments on the COIL-20 robotic perception dataset demonstrate that PCN-TA achieves 10% fewer weight updates compared to backpropagation and requires 50% fewer inference steps than baseline PC networks. These efficiency gains directly translate to reduced computational overhead for moving another step toward edge deployment and real-time adaptation support in resource-constrained robotic systems. The biologically-inspired nature of our approach also makes it a promising candidate for future neuromorphic hardware implementations, enabling efficient online learning at the edge.

Robotics0 citations2025-10-28arXiv ->

Enhancing Vision-Language Models for Autonomous Driving through Task-Specific Prompting and Spatial Reasoning

Aodi Wu, Xubo Luo

This technical report presents our solution for the RoboSense Challenge at IROS 2025, which evaluates Vision-Language Models (VLMs) on autonomous driving scene understanding across perception, prediction, planning, and corruption detection tasks. We propose a systematic framework built on four core components. First, a Mixture-of-Prompts router classifies questions and dispatches them to task-specific expert prompts, eliminating interference across diverse question types. Second, task-specific prompts embed explicit coordinate systems, spatial reasoning rules, role-playing, Chain-of-Thought/Tree-of-Thought reasoning, and few-shot examples tailored to each task. Third, a visual assembly module composes multi-view images with object crops, magenta markers, and adaptive historical frames based on question requirements. Fourth, we configure model inference parameters (temperature, top-p, message roles) per task to optimize output quality. Implemented on Qwen2.5-VL-72B, our approach achieves 70.87% average accuracy on Phase-1 (clean data) and 72.85% on Phase-2 (corrupted data), demonstrating that structured prompting and spatial grounding substantially enhance VLM performance on safety-critical autonomous driving tasks. Code and prompt are available at https://github.com/wuaodi/UCAS-CSU-phase2.

Robotics0 citations2025-10-27arXiv ->

Stand, Walk, Navigate: Recovery-Aware Visual Navigation on a Low-Cost Wheeled Quadruped

Jans Solano, Diego Quiroz

Wheeled-legged robots combine the efficiency of wheels with the obstacle negotiation of legs, yet many state-of-the-art systems rely on costly actuators and sensors, and fall-recovery is seldom integrated, especially for wheeled-legged morphologies. This work presents a recovery-aware visual-inertial navigation system on a low-cost wheeled quadruped. The proposed system leverages vision-based perception from a depth camera and deep reinforcement learning policies for robust locomotion and autonomous recovery from falls across diverse terrains. Simulation experiments show agile mobility with low-torque actuators over irregular terrain and reliably recover from external perturbations and self-induced failures. We further show goal directed navigation in structured indoor spaces with low-cost perception. Overall, this approach lowers the barrier to deploying autonomous navigation and robust locomotion policies in budget-constrained robotic platforms.

Robotics0 citations2025-10-27arXiv ->

DPGLA: Bridging the Gap between Synthetic and Real Data for Unsupervised Domain Adaptation in 3D LiDAR Semantic Segmentation

Wanmeng Li, Simone Mosco, Daniel Fusaro, Alberto Pretto

Annotating real-world LiDAR point clouds for use in intelligent autonomous systems is costly. To overcome this limitation, self-training-based Unsupervised Domain Adaptation (UDA) has been widely used to improve point cloud semantic segmentation by leveraging synthetic point cloud data. However, we argue that existing methods do not effectively utilize unlabeled data, as they either rely on predefined or fixed confidence thresholds, resulting in suboptimal performance. In this paper, we propose a Dynamic Pseudo-Label Filtering (DPLF) scheme to enhance real data utilization in point cloud UDA semantic segmentation. Additionally, we design a simple and efficient Prior-Guided Data Augmentation Pipeline (PG-DAP) to mitigate domain shift between synthetic and real-world point clouds. Finally, we utilize data mixing consistency loss to push the model to learn context-free representations. We implement and thoroughly evaluate our approach through extensive comparisons with state-of-the-art methods. Experiments on two challenging synthetic-to-real point cloud semantic segmentation tasks demonstrate that our approach achieves superior performance. Ablation studies confirm the effectiveness of the DPLF and PG-DAP modules. We release the code of our method in this paper.

Robotics0 citations2025-10-27arXiv ->

Awakening Facial Emotional Expressions in Human-Robot

Yongtong Zhu, Lei Li, Iggy Qian, WenBin Zhou, Ye Yuan et al.

The facial expression generation capability of humanoid social robots is critical for achieving natural and human-like interactions, playing a vital role in enhancing the fluidity of human-robot interactions and the accuracy of emotional expression. Currently, facial expression generation in humanoid social robots still relies on pre-programmed behavioral patterns, which are manually coded at high human and time costs. To enable humanoid robots to autonomously acquire generalized expressive capabilities, they need to develop the ability to learn human-like expressions through self-training. To address this challenge, we have designed a highly biomimetic robotic face with physical-electronic animated facial units and developed an end-to-end learning framework based on KAN (Kolmogorov-Arnold Network) and attention mechanisms. Unlike previous humanoid social robots, we have also meticulously designed an automated data collection system based on expert strategies of facial motion primitives to construct the dataset. Notably, to the best of our knowledge, this is the first open-source facial dataset for humanoid social robots. Comprehensive evaluations indicate that our approach achieves accurate and diverse facial mimicry across different test subjects.

Robotics0 citations2025-10-27arXiv ->

ManiDP: Manipulability-Aware Diffusion Policy for Posture-Dependent Bimanual Manipulation

Zhuo Li, Junjia Liu, Dianxi Li, Tao Teng, Miao Li et al.

Recent work has demonstrated the potential of diffusion models in robot bimanual skill learning. However, existing methods ignore the learning of posture-dependent task features, which are crucial for adapting dual-arm configurations to meet specific force and velocity requirements in dexterous bimanual manipulation. To address this limitation, we propose Manipulability-Aware Diffusion Policy (ManiDP), a novel imitation learning method that not only generates plausible bimanual trajectories, but also optimizes dual-arm configurations to better satisfy posture-dependent task requirements. ManiDP achieves this by extracting bimanual manipulability from expert demonstrations and encoding the encapsulated posture features using Riemannian-based probabilistic models. These encoded posture features are then incorporated into a conditional diffusion process to guide the generation of task-compatible bimanual motion sequences. We evaluate ManiDP on six real-world bimanual tasks, where the experimental results demonstrate a 39.33$\%$ increase in average manipulation success rate and a 0.45 improvement in task compatibility compared to baseline methods. This work highlights the importance of integrating posture-relevant robotic priors into bimanual skill diffusion to enable human-like adaptability and dexterity.

MPC/Planning0 citations2025-10-26arXiv ->

TWC-SLAM: Multi-Agent Cooperative SLAM with Text Semantics and WiFi Features Integration for Similar Indoor Environments

Chunyu Li, Shoubin Chen, Dong Li, Weixing Xue, Qingquan Li

Multi-agent cooperative SLAM often encounters challenges in similar indoor environments characterized by repetitive structures, such as corridors and rooms. These challenges can lead to significant inaccuracies in shared location identification when employing point cloud-based techniques. To mitigate these issues, we introduce TWC-SLAM, a multi-agent cooperative SLAM framework that integrates text semantics and WiFi signal features to enhance location identification and loop closure detection. TWC-SLAM comprises a single-agent front-end odometry module based on FAST-LIO2, a location identification and loop closure detection module that leverages text semantics and WiFi features, and a global mapping module. The agents are equipped with sensors capable of capturing textual information and detecting WiFi signals. By correlating these data sources, TWC-SLAM establishes a common location, facilitating point cloud alignment across different agents' maps. Furthermore, the system employs loop closure detection and optimization modules to achieve global optimization and cohesive mapping. We evaluated our approach using an indoor dataset featuring similar corridors, rooms, and text signs. The results demonstrate that TWC-SLAM significantly improves the performance of cooperative SLAM systems in complex environments with repetitive architectural features.

Learning0 citations2025-10-26arXiv ->

SCAL for Pinch-Lifting: Complementary Rotational and Linear Prototypes for Environment-Adaptive Grasping

Wentao Guo, Wenzeng Zhang

This paper presents environment-adaptive pinch-lifting built on a slot-constrained adaptive linkage (SCAL) and instantiated in two complementary fingers: SCAL-R, a rotational-drive design with an active fingertip that folds inward after contact to form an envelope, and SCAL-L, a linear-drive design that passively opens on contact to span wide or weak-feature objects. Both fingers convert surface following into an upward lifting branch while maintaining fingertip orientation, enabling thin or low-profile targets to be raised from supports with minimal sensing and control. Two-finger grippers are fabricated via PLA-based 3D printing. Experiments evaluate (i) contact-preserving sliding and pinch-lifting on tabletops, (ii) ramp negotiation followed by lift, and (iii) handling of bulky objects via active enveloping (SCAL-R) or contact-triggered passive opening (SCAL-L). Across dozens of trials on small parts, boxes, jars, and tape rolls, both designs achieve consistent grasps with limited tuning. A quasi-static analysis provides closed-form fingertip-force models for linear parallel pinching and two-point enveloping, offering geometry-aware guidance for design and operation. Overall, the results indicate complementary operating regimes and a practical path to robust, environment-adaptive grasping with simple actuation.

Learning0 citations2025-10-26arXiv ->

Bag-of-Word-Groups (BoWG): A Robust and Efficient Loop Closure Detection Method Under Perceptual Aliasing

Xiang Fei, Tina Tian, Howie Choset, Lu Li

Loop closure is critical in Simultaneous Localization and Mapping (SLAM) systems to reduce accumulative drift and ensure global mapping consistency. However, conventional methods struggle in perceptually aliased environments, such as narrow pipes, due to vector quantization, feature sparsity, and repetitive textures, while existing solutions often incur high computational costs. This paper presents Bag-of-Word-Groups (BoWG), a novel loop closure detection method that achieves superior precision-recall, robustness, and computational efficiency. The core innovation lies in the introduction of word groups, which captures the spatial co-occurrence and proximity of visual words to construct an online dictionary. Additionally, drawing inspiration from probabilistic transition models, we incorporate temporal consistency directly into similarity computation with an adaptive scheme, substantially improving precision-recall performance. The method is further strengthened by a feature distribution analysis module and dedicated post-verification mechanisms. To evaluate the effectiveness of our method, we conduct experiments on both public datasets and a confined-pipe dataset we constructed. Results demonstrate that BoWG surpasses state-of-the-art methods, including both traditional and learning-based approaches, in terms of precision-recall and computational efficiency. Our approach also exhibits excellent scalability, achieving an average processing time of 16 ms per image across 17,565 images in the Bicocca25b dataset.

Robotics0 citations2025-10-25arXiv ->

Estimating Continuum Robot Shape under External Loading using Spatiotemporal Neural Networks

Enyi Wang, Zhen Deng, Chuanchuan Pan, Bingwei He, Jianwei Zhang

This paper presents a learning-based approach for accurately estimating the 3D shape of flexible continuum robots subjected to external loads. The proposed method introduces a spatiotemporal neural network architecture that fuses multi-modal inputs, including current and historical tendon displacement data and RGB images, to generate point clouds representing the robot's deformed configuration. The network integrates a recurrent neural module for temporal feature extraction, an encoding module for spatial feature extraction, and a multi-modal fusion module to combine spatial features extracted from visual data with temporal dependencies from historical actuator inputs. Continuous 3D shape reconstruction is achieved by fitting Bézier curves to the predicted point clouds. Experimental validation demonstrates that our approach achieves high precision, with mean shape estimation errors of 0.08 mm (unloaded) and 0.22 mm (loaded), outperforming state-of-the-art methods in shape sensing for TDCRs. The results validate the efficacy of deep learning-based spatiotemporal data fusion for precise shape estimation under loading conditions.

Robotics0 citations2025-10-25arXiv ->

STG-Avatar: Animatable Human Avatars via Spacetime Gaussian

Guangan Jiang, Tianzi Zhang, Dong Li, Zhenjun Zhao, Haoang Li et al.

Realistic animatable human avatars from monocular videos are crucial for advancing human-robot interaction and enhancing immersive virtual experiences. While recent research on 3DGS-based human avatars has made progress, it still struggles with accurately representing detailed features of non-rigid objects (e.g., clothing deformations) and dynamic regions (e.g., rapidly moving limbs). To address these challenges, we present STG-Avatar, a 3DGS-based framework for high-fidelity animatable human avatar reconstruction. Specifically, our framework introduces a rigid-nonrigid coupled deformation framework that synergistically integrates Spacetime Gaussians (STG) with linear blend skinning (LBS). In this hybrid design, LBS enables real-time skeletal control by driving global pose transformations, while STG complements it through spacetime adaptive optimization of 3D Gaussians. Furthermore, we employ optical flow to identify high-dynamic regions and guide the adaptive densification of 3D Gaussians in these regions. Experimental results demonstrate that our method consistently outperforms state-of-the-art baselines in both reconstruction quality and operational efficiency, achieving superior quantitative metrics while retaining real-time rendering capabilities. Our code is available at https://github.com/jiangguangan/STG-Avatar

ICRA 2026 | 46 papers
CBF Related Papers
Robotics0 citations2026-06-23arXiv ->

Causality-Based Parametric Control Barrier Function for Safe Multi-Vehicle Interaction

Yiwei Lyu, Caleb Chang, John M. Dolan

Safe control has been widely studied in various safety-critical applications, for instance, autonomous driving. In order to ensure the autonomous vehicle does not collide with other vehicles, it is essential to obtain an accurate expectation of surrounding vehicles' behavior and react adaptively. Instead of assuming fully cooperative and homogeneous vehicles using the same safety-critical controllers, recent works have been exploring different data-driven approaches to model the neighboring vehicles' underlying controllers with observed data. However, existing works either suffer from 1) the inter-vehicle influence during the multi-vehicle interaction, which makes it hard to determine the causality of surrounding vehicles' behavior in controller modeling, or 2) being dominated by the worst-case analysis, which may lead to overly conservative behavior. In this paper, we extend the prior work on Parametric-Control Barrier Function (Parametric-CBF) to multi-robot interactions with embedded causality inference to explicitly reason over the inter-vehicle influence. Given the learned Causality-based Parametric-CBF, we present an adaptive safety-critical controller that allows the ego vehicle to safely react to surrounding vehicles with the learned expectation. We demonstrate that by leveraging the motion flexibility among multi-vehicle systems, task efficiency can be greatly improved in various interaction-intensive scenarios.

Robotics0 citations2026-05-29arXiv ->

Geometry-Aware Control Barrier Functions for Collision Avoidance via Bernstein Polynomial Approximations

Siwon Jo, Yanze Zhang, Yupeng Yang, Wenhao Luo

Safe navigation often relies on well-defined conditions based on the shape of robots and obstacles, and can be challenging when they have irregular geometries. While Control Barrier Functions (CBFs) offer an efficient mechanism to enforce safe set forward invariance, common shape surrogates (e.g., spheres or super-ellipsoids) either are overly conservative in unstructured scenes or require many local primitives, which inflates constraint counts and degrades real-time performance. In this paper, we introduce a novel geometry-aware Control Barrier Function (CBF) based on Bernstein-Polynomial Signed Distance Fields (BP-SDFs). It provides a unified way to represent the obstacles and robots, so as to represent the barrier function with a unified minimum distance. Benefiting from the differentiability of the Bernstein polynomials, one can easily enforce the control constraints in a closed loop. We validate the method's efficiency and performance to guarantee safety in single-robot navigation and heterogeneous multi-robot collision avoidance via simulations under different environments.

Robotics0 citations2026-03-31arXiv ->

SafeDMPs: Integrating Formal Safety with DMPs for Adaptive HRI

Soumyodipta Nath, Pranav Tiwari, Ravi Prakash

Robots operating in human-centric environments must be both robust to disturbances and provably safe from collisions. Achieving these properties simultaneously and efficiently remains a central challenge. While Dynamic Movement Primitives (DMPs) offer inherent stability and generalization from single demonstrations, they lack formal safety guarantees. Conversely, formal methods like Control Barrier Functions (CBFs) provide provable safety but often rely on computationally expensive, real-time optimization, hindering their use in high-frequency control. This paper introduces SafeDMPs, a novel framework that resolves this trade-off. We integrate the closed-form efficiency and dynamic robustness of DMPs with a provably safe, non-optimization-based control law derived from Spatio-Temporal Tubes (STTs). This synergy allows us to generate motions that are not only robust to perturbations and adaptable to new goals, but also guaranteed to avoid static and dynamic obstacles. Our approach achieves a closed-form solution for a problem that traditionally requires online optimization. Experimental results on a 7-DOF robot manipulator demonstrate that SafeDMPs is orders of magnitude faster and more accurate than optimization-based baselines, making it an ideal solution for real-time, safe, and collaborative robotics.

MPC/Planning0 citations2026-03-09arXiv ->

SEP-NMPC: Safety Enhanced Passivity-Based Nonlinear Model Predictive Control for a UAV Slung Payload System

Seyedreza Rezaei, Junjie Kang, Amaldev Haridevan, Jinjun Shan

Model Predictive Control (MPC) is widely adopted for agile multirotor vehicles, yet achieving both stability and obstacle-free flight is particularly challenging when a payload is suspended beneath the airframe. This paper introduces a Safety Enhanced Passivity-Based Nonlinear MPC (SEP-NMPC) that provides formal guarantees of stability and safety for a quadrotor transporting a slung payload through cluttered environments. Stability is enforced by embedding a strict passivity inequality, which is derived from a shaped energy storage function with adaptive damping, directly into the NMPC. This formulation dissipates excess energy and ensures asymptotic convergence despite payload swings. Safety is guaranteed through high-order control barrier functions (HOCBFs) that render user-defined clearance sets forward-invariant, obliging both the quadrotor and the swinging payload to maintain separation while interacting with static and dynamic obstacles. The optimization remains quadratic-program compatible and is solved online at each sampling time without gain scheduling or heuristic switching. Extensive simulations and real-world experiments confirm stable payload transport, collision-free trajectories, and real-time feasibility across all tested scenarios. The SEP-NMPC framework therefore unifies passivity-based closed-loop stability with HOCBF-based safety guarantees for UAV slung-payload transportation.

Robotics0 citations2026-03-02arXiv ->

A Safety-Aware Shared Autonomy Framework with BarrierIK Using Control Barrier Functions

Berk Guler, Kay Pompetzki, Yuanzheng Sun, Simon Manschitz, Jan Peters

Shared autonomy blends operator intent with autonomous assistance. In cluttered environments, linear blending can produce unsafe commands even when each source is individually collision-free. Many existing approaches model obstacle avoidance through potentials or cost terms, which only enforce safety as a soft constraint. In contrast, safety-critical control requires hard guarantees. We investigate the use of control barrier functions (CBFs) at the inverse kinematics (IK) layer of shared autonomy, targeting post-blend safety while preserving task performance. Our approach is evaluated in simulation on representative cluttered environments and in a VR teleoperation study comparing pure teleoperation with shared autonomy. Across conditions, employing CBFs at the IK layer reduces violation time and increases minimum clearance while maintaining task performance. In the user study, participants reported higher perceived safety and trust, lower interference, and an overall preference for shared autonomy with our safety filter. Additional materials available at https://berkguler.github.io/barrierik.

Robotics0 citations2025-11-09arXiv ->

From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policies

Ralf Römer, Julian Balletshofer, Jakob Thumm, Marco Pavone, Angela P. Schoellig et al.

Diffusion policies (DPs) achieve state-of-the-art performance on complex manipulation tasks by learning from large-scale demonstration datasets, often spanning multiple embodiments and environments. However, they cannot guarantee safe behavior, requiring external safety mechanisms. These, however, alter actions in ways unseen during training, causing unpredictable behavior and performance degradation. To address these problems, we propose path-consistent safety filtering (PACS) for DPs. Our approach performs path-consistent braking on a trajectory computed from the sequence of generated actions. In this way, we keep the execution consistent with the training distribution of the policy, maintaining the learned, task-completing behavior. To enable real-time deployment and handle uncertainties, we verify safety using set-based reachability analysis. Our experimental evaluation in simulation and on three challenging real-world human-robot interaction tasks shows that PACS (a) provides formal safety guarantees in dynamic environments, (b) preserves task success rates, and (c) outperforms reactive safety approaches, such as control barrier functions, by up to 68 % in terms of task success. Videos are available at our project website: https://tum-lsy.github.io/pacs.

Robotics0 citations2025-10-16arXiv ->

CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions

Lizhi Yang, Blake Werner, Massimiliano de Sa, Aaron D. Ames

Reinforcement learning (RL), while powerful and expressive, can often prioritize performance at the expense of safety. Yet safety violations can lead to catastrophic outcomes in real-world deployments. Control Barrier Functions (CBFs) offer a principled method to enforce dynamic safety -- traditionally deployed online via safety filters. While the result is safe behavior, the fact that the RL policy does not have knowledge of the CBF can lead to conservative behaviors. This paper proposes CBF-RL, a framework for generating safe behaviors with RL by enforcing CBFs in training. CBF-RL has two key attributes: (1) minimally modifying a nominal RL policy to encode safety constraints via a CBF term, (2) and safety filtering of the policy rollouts in training. Theoretically, we prove that continuous-time safety filters can be deployed via closed-form expressions on discrete-time roll-outs. Practically, we demonstrate that CBF-RL internalizes the safety constraints in the learned policy -- both enforcing safer actions and biasing towards safer rewards -- enabling safe deployment without the need for an online safety filter. We validate our framework through ablation studies on navigation tasks and on the Unitree G1 humanoid robot, where CBF-RL enables safer exploration, faster convergence, and robust performance under uncertainty, enabling the humanoid robot to avoid obstacles and climb stairs safely in real-world settings without a runtime safety filter.

Robotics0 citations2025-10-01arXiv ->

Beyond Collision Cones: Dynamic Obstacle Avoidance for Nonholonomic Robots via Dynamic Parabolic Control Barrier Functions

Hun Kuk Park, Taekyung Kim, Dimitra Panagou

Control Barrier Functions (CBFs) are a powerful tool for ensuring the safety of autonomous systems, yet applying them to nonholonomic robots in cluttered, dynamic environments remains an open challenge. State-of-the-art methods often rely on collision-cone or velocity-obstacle constraints which, by only considering the angle of the relative velocity, are inherently conservative and can render the CBF-based quadratic program infeasible, particularly in dense scenarios. To address this issue, we propose a Dynamic Parabolic Control Barrier Function (DPCBF) that defines the safe set using a parabolic boundary. The parabola's vertex and curvature dynamically adapt based on both the distance to an obstacle and the magnitude of the relative velocity, creating a less restrictive safety constraint. We prove that the proposed DPCBF is valid for a kinematic bicycle model subject to input constraints. Extensive comparative simulations demonstrate that our DPCBF-based controller significantly enhances navigation success rates and QP feasibility compared to baseline methods. Our approach successfully navigates through dense environments with up to 100 dynamic obstacles, scenarios where collision cone-based methods fail due to infeasibility.

Other Papers
Learning0 citations2026-07-20arXiv ->

Robust Multimodal Dynamic Object Segmentation

Zhe Xin, Hanzhi Chang, Penghui Huang, Yinian Mao, Guoquan Huang

Dynamic object segmentation plays a critical role in many visual applications such as static scene reconstruction from dynamic videos. However, existing optical flow-based methods fail to ensure consistent static/dynamic segmentation along object boundaries, while 3D reconstruction-based approaches are highly sensitive to reconstruction errors. To address these limitations, we present a dynamic object segmentation framework that can generate both precise and complete dynamic masks by integrating multimodal cues including 2D point tracks, 3D reconstruction, and semantic information. We design a network combining Transformer architectures with feature clustering aggregation modules to perform static/dynamic classification of multimodal feature trajectories. It enables the model to adaptively determine which type of feature should dominate based on the characteristics of each scene, while also mitigating the impact of feature degradation. Additionally, we introduce a novel point-query-based SAM post-processing method capable of handling multiple objects within a single mask. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in both dynamic object segmentation and static scene reconstruction tasks.

Robotics0 citations2026-07-20arXiv ->

Leveraging Two Robotic Arms for Tight Assembly Performance Gains

Dror Livnat, Yuval Lavi, Michael M. Bilevich, Dan Halperin

We provide a novel end-to-end framework for the execution of an assembly operation by two robotic arms, given the digital CAD models of the parts and their desired relative placement in their assembled state. We analyze and demonstrate the advantages of using two robotic arms simultaneously in tight assembly operations, compared to single-arm systems. Our method is implemented in both simulation and using physical robots. It provides theoretical guarantees on execution time and trajectory accuracy, supported by empirical evidence. In particular, we show that coordinated movement of two arms reduces average execution time by more than 50% compared to using a single arm only, produces higher-quality trajectories, and accelerates the search for valid robot placements. Furthermore, we establish bounds on the required dimensions of the robotic cell. Our open source software together with real-life video demonstrations are available in our project page.

Robotics0 citations2026-07-20arXiv ->

Lifelong Localization in Dynamic Indoor Environments Combining Odometry with Sparse Distance Sampling

Michael M. Bilevich, Tomer Buber, Dan Halperin

Localization is a key task in robot navigation, and many techniques exist for it. In many plausible scenarios, a robot might face unforeseen, dynamic obstacles, rendering any pre-determined map inaccurate for localization. In this work, we propose a robust lifelong localization framework in dynamic planar indoor environments, using the robot's odometry and sparse distance sampling. We demonstrate how distance samples can be used to provide a robust prior on the robot's location. This technique can solve the kidnapped robot problem in real time, up to symmetries. Based on insights from real-world recorded data, we also account for dynamic obstacles. We then fuse this prior, over time, with the odometry to converge to the robot's location. A central property of our method is that it provably converges to the robot's ground truth pose even in large indoor environments when the environment is static. We further show that this guarantee also holds in dynamic environments, as long as the nature of those changes has been correctly learned. We demonstrate the effectiveness of our approach in different real-world indoor environments. In particular, we achieve a localization comparable to SLAM with merely a few (sixteen) distance samples, as opposed to the full LiDAR range. Sufficing with only sparse distance sampling is advantageous in terms of sensor cost, privacy, storage space, and transmission bandwidth.

Robotics0 citations2026-07-16arXiv ->

Environment Design for Reliable Shared Autonomy with Probabilistic Guarantees

Yi-Shiuan Tung, Himanshu Gupta, Gyanig Kumar, Heyang Huang, Bradley Hayes et al.

Shared autonomy enables humans and robots to collaboratively perform tasks by combining human input with autonomous assistance. Most prior work focuses on improving intent inference under a fixed environment, overlooking how workspace design itself affects inference difficulty. We observe that the physical arrangement of objects directly influences the separability of candidate goals under noisy user inputs. We formulate workspace design as an optimization problem and derive a probabilistic correctness guarantee under a bounded noise model. Through simulation experiments across multiple tabletop scenarios, we show that optimized layouts improve goal inference reliability and reduce ambiguity compared to baseline arrangements. We further demonstrate a real-world shared autonomy system that integrates the proposed inference framework. This highlights the role of environment design as a complementary axis for improving shared autonomy systems.

Robotics0 citations2026-07-16arXiv ->

Risk-Aware Preference Learning for Stochastic Outcomes

Yi-Shiuan Tung, Yuni Wu, Wei Jiang, Alessandro Roncone, Bradley Hayes

Learning reward functions from human preferences is a widely used approach for aligning robot behavior with user expectations in human-robot interaction. Most existing approaches assume that humans evaluate uncertain outcomes using expected utility (EU), aggregating outcome utilities linearly with their probabilities. However, behavioral evidence shows that humans are systematically risk-sensitive, overweighting rare negative events and exhibiting loss aversion. We study the consequences of this mismatch in social robot navigation, where safety-critical outcomes (e.g., collisions) are rare but highly consequential. We compare EU with Cumulative Prospect Theory (CPT), a nonlinear model of human decision-making, within a Bradley-Terry preference learning framework. Our preliminary experiments show that when preferences are generated by risk-sensitive users, CPT-based learners recover reward functions with substantially lower regret compared to EU-based learners. Our results highlight the importance of modeling human risk sensitivity when learning rewards from preferences over stochastic robot outcomes.

Robotics0 citations2026-07-16arXiv ->

Curvature-Constrained and Constant-Speed Distributed Simultaneous Arrival Control for Multi-Robot Systems

Zhouru Xiao, Yang Lu, Weijia Yao, Min Liu, Yaonan Wang

The simultaneous arrival of multiple mobile robots at a target point is crucial for cooperation tasks such as cooperative encirclement, disaster relief, and environmental monitoring. Although the simultaneous arrival problem itself is already complex, the problem becomes more challenging when there are constraints on the robot trajectory curvatures and the speeds are required to be constant (possibly different for different robots), and the control law for robots needs to be distributed. These constraints are typical for a multi-robot system consisting of, e.g., fixed-wing UAVs. To address this challenge, this paper proposes a distributed switching control method based on the maximum consensus protocol. By exploiting the geometric properties of Dubins paths along with optimization principles, a virtual time variable is introduced, and a hybrid control law that combines optimal control with saturated proportional control is designed. Under the proposed control law, each robot is driven to approach the maximum virtual time among its neighbors, thereby achieving simultaneous arrival under some mild conditions. Furthermore, we prove that in certain cases the proposed method attains a theoretically optimal arrival time. The approach is scalable and real-time, with low communication overhead. Its effectiveness and robustness are validated through extensive simulations and experiments.

Robotics0 citations2026-07-16arXiv ->

Hybrid Rigid-Soft Robotic Gripper with Shape Adaptation, Uniform Force Distribution, and Self-Locking Capabilities

Xi Chen, Yun Wang, Lichao Yang, Haitao Li, Ya Xiong

Conventional robotic grippers face a significant challenge in agricultural automation: the trade-off between compliant, adaptive grasping, pressure balancing among all joints, and high load capacity, often at the cost of high energy consumption. This paper presents a novel hybrid rigid-soft gripper that integrated low-cost, membrane-based pneumatic actuators with 3D-printed dual ratchet-pawl mechanisms to simultaneously achieve shape adaptation, uniform force distribution, and energy-free self-locking. The dual-ratchet structure assembled in an offset configuration significantly increased the angular resolution of the joint locking mechanism. Key experimental results demonstrated the gripper's superior performance: a remarkable maximum load capacity of 4200 g, far exceeding that of conventional soft grippers (45-210 g); more uniform force distribution across object sizes (1.75-35.29% difference ratio) compared to a rigid gripper (56.77-66.44%), with peak contact forces remaining below surface damage thresholds; and a 50.05% reduction in total energy consumption to 42.6 J per grasp cycle, achieved by eliminating the need for continuous pneumatic pressure through the self-locking mechanism, compared to 85.28 J for a conventional soft gripper. The combination of additive manufacturing for ratchets and commercially available materials for pneumatic chambers ensured a low-cost and easily fabricated design. These findings validated that the proposed gripper successfully bridged the gap between soft compliance and rigid reliability, offering a robust and efficient solution for scalable agricultural harvesting and manipulation tasks.

Robotics0 citations2026-07-15arXiv ->

Deformable State Estimation for Autonomous Surgical Tissue Retraction Under Partial Observability

Everest Yang, Skye Thompson, George D. Konidaris

Surgical tissue retraction requires effective manipulation planning under partial and noisy perception. We study state estimation for deformable tissue retraction, where only sparse observations of the tissue surface are available at decision time. We propose a learned state estimator that reconstructs the full deformable mesh state from 40 noisy vertex observations. The estimator combines a multilayer perceptron with a low-dimensional PCA latent representation and is trained using geometry-aware regularization that encourages smooth and physically plausible deformations. We evaluate the approach in a 2D deformable sheet simulation using single-step and multi-step retraction planning. Results show that the learned estimator achieves 98.1% of oracle performance in multi-step retraction while supporting efficient inference. These results demonstrate that learned, geometry-regularized state estimation can support effective deformable manipulation under realistic perception constraints.

MPC/Planning0 citations2026-07-12arXiv ->

Mapping Pamir: Multi-Session Visual-Inertial SLAM and 3D Reconstruction of an Underwater Shipwreck

Michalis Chatzispyrou, Luke Horgan, Hyunkil Hwang, Harish Sathishchandra, Chinmay Burgul et al.

This paper presents a framework for multi-session mapping of underwater environments utilizing an affordable action camera. The Visual-Inertial data are augmented by water depth recordings from a dive computer. SVIn2, an open-source VI-SLAM framework, is utilized to generate a trajectory and a sparse reconstruction for each session. Utilizing the keyframes extracted from SVIn2 and the estimated camera poses, a Structure-from-Motion (SfM) framework, COLMAP, is employed for global optimization and to produce a dense reconstruction of the target environment. The presence of calibration targets at fixed locations, when available, is used to estimate the coordinate transformation between different data collection sessions, thus transforming the different sessions into the same coordinate frame. The proposed pipeline is employed for the mapping of a shipwreck off the coast of Barbados. For the first time, both the exterior and the accessible interior parts of the wreck were mapped in two sessions, while a third session employed two cameras with different fields of view.

Robotics0 citations2026-07-12arXiv ->

Compositional Context Fine-Tuning Vision-Language Model for Complex Assembly Action Understanding from Videos

Hao Zheng, Jinyi Huang, Tiantian Zheng, Xun Xu, Tuka Alhanai

Assembly action understanding is a key enabler for effective human-robot collaborative assembly, yet it remains challenging due to subtle motions and fine-grained hand-object interactions. We adapt vision-language models (VLMs) to this challenging domain with Compositional Context Fine-Tuning (CCFT), a method that decomposes assembly actions into semantic elements (Verb, Object, Tool) and fine-tunes VLMs to recognize each action element using templated question-answering pairs. This approach ensures near-deterministic outputs. To enable efficient and effective multi-task learning under limited data, a Layer-Partitioned Alternating Training (LP-AT) method is presented, which assigns distinct model layers to recognize specific action elements through element-specific low-rank adapters. LP-AT alternates weight updates across element-specific adapters, reducing cross-task interference while enabling per-adapter hyperparameter optimization. Furthermore, we create HA-ViD-VQA and IKEA-ASM-VQA datasets from existing assembly video datasets. Extensive experiments on these datasets demonstrate that our method consistently outperforms strong action recognition baselines while providing interpretable element-level predictions that can support diverse downstream applications.

Robotics0 citations2026-07-05arXiv ->

SurgAM: Surgical Affordance Map Prediction with Multimodal Feature Fusion for Robot Autonomy

Lei Song, Yonghao Long, Mengya Xu, Jiayi Geng, Xiuyuan Chen et al.

Surgical automation is being increasingly studied, yet bridging visual scene understanding with autonomous action planning remains a fundamental challenge. While much research effort has been made on scene perception (e.g., tool recognition and scene segmentation), understanding and predicting actionable possibilities for surgical automation is still underexplored. In this paper, we introduce surgical affordance prediction, which identifies actionable regions for fundamental surgical actions from visual data. Specifically, a novel adaptive feature fusion framework is proposed that leverages the complementary strengths of a self-supervised vision transformer encoder for its superior semantic understanding and a large-scale generative model encoder for its spatially-aware capability. Furthermore, we introduce a hierarchical prompt learning mechanism to adapt to varying procedural contexts. Finally, a scene-guided attention decoder is proposed to focus on critical surgical areas while suppressing background distractions. To validate the effectiveness, we established a new dataset, derived from publicly available surgical datasets with affordance annotations for three basic surgical actions: aspiration, clipping, and retraction. Extensive experiments demonstrate that our approach achieves state-of-the-art performance. Moreover, we validate our framework's applicability for downstream automation on a realistic lung and prostate phantom, and results show that the predicted affordance maps successfully enable autonomous surgical actions.

Robotics0 citations2026-07-03arXiv ->

CoorGrasp: Coordinated Contact Control for Adaptive Dexterous Grasping Under Uncertainty

Mingrui Yu, Yongpeng Jiang, Yongyi Jia, Ren Yi, Xiang Li

While recent research has focused heavily on dexterous grasp pose generation, less attention has been devoted to the execution of planned grasps. Under shape and position uncertainty, open-loop execution often yields uncoordinated contacts, causing undesired in-hand object motion and even grasp failures. To address this, this paper proposes a tactile-driven model predictive controller for adaptive and delicate execution of diverse dexterous grasps. Our approach emphasizes multi-contact coordination across both approaching and grasping phases, with three key novelties: (i) coordination-aware phase separation, (ii) arm-hand coordination to compensate for position errors, and (iii) adaptive force coordination to increase contact forces in a balanced manner. An analytical model is employed to relate contact forces to robot joint motions for predictive control. Our formulation imposes no restrictions on grasp types or contact configurations and integrates seamlessly with state-of-the-art grasp pose generation methods. We validate the approach through large-scale simulations involving 15k grasps across 478 objects on three robotic hands, and real-world experiments on 8 objects. Results demonstrate that our method achieves higher grasp success rates and reduced undesired object movements.

Robotics0 citations2026-07-03arXiv ->

iVISION-2DCD: A Long-Term Change Detection Dataset for Large-Scale Outdoor Construction Monitoring

Dayou Mao, Yuchen Lin, Ashkan Ebadi, John Zelek, Alexander Wong et al.

Automation in construction is essential for reducing costs and human errors in large-scale projects. We approach the construction progress monitoring from the aspect of detecting changes in construction sites. As construction buildings continue to evolve in geometry and appearance over time, change detection need to be performed from arbitrary camera viewpoints. This necessitates developing 2D Change Detection (2DCD) algorithms that operate robustly across diverse camera perspectives at construction sites. While developing and evaluating such systems is data-intensive, no open-source benchmark dataset exists at the intersection of 2D change detection and construction automation research. Data collection using Unmanned Aerial Vehicles (UAVs) is gaining its popularity in outdoor large-scale surveying. However, in active construction sites conducting drone missions equipped with high-end sensors imposes safety concerns. Flight trajectory and collected camera viewpoints can be significantly limited. To address this critical gap, we introduce iVISION-2DCD, a large-scale synthetically generated dataset from dense LiDAR point clouds with photorealistic input images and accurate ground truth annotations. Our dataset formally defines the problem of viewpoint-robust 2DCD at construction sites and captures the inherent complexities of real-world deployment. In this paper, we present our systematic methodology for synthetic data generation, developing novel view synthesis techniques to overcome bi-temporal alignment and viewpoint diversity challenges, and implementing semi-automated semantic segmentation with change label generation while preserving challenging real-world cases. Benchmark evaluations using state-of-the-art 2DCD algorithms demonstrate that iVISION-2DCD poses novel research challenges for the computer vision and robotics communities.

Robotics0 citations2026-06-30arXiv ->

CoDex: Learning Compositional Dexterous Functional Manipulation without Demonstrations

Bowen Jiang, William Painter Reger, Roberto Martin-Martin

In this work, we study Compositional Dexterous Functional Object Manipulation (CD-FOM): tasks such as aiming and actuating a spray bottle on a plant or a glue gun on wood, which require both actuating an object's internal mechanism and controlling its pose to apply the object's function to the environment. These tasks pose significant challenges for robots due to the demanding integration of semantic understanding of the object's function, actuation mode, and application area with intricate physical dexterity to manage grasp stability, movement trajectory, and actuation. We introduce CoDex, a zero-demonstration framework that autonomously discovers CD-FOM manipulation strategies. CoDex uses vision-language models (VLMs) to infer semantic constraints from the task and scene. These constraints guide analytic constrained optimization to generate a short list of functional grasp candidates that can be efficiently refined with reinforcement learning to generate full grasp-move-actuate policies transferable from simulation to the real world. We evaluate CoDex on a 7-DoF robot arm with a 16-DoF multi-fingered hand across six CD-FOM tasks involving previously unseen objects with internal mechanisms, including spray bottles, hot glue guns, air dusters, flashlights, and pepper grinders, and their application to unseen target objects, showcasing its ability to autonomously discover and execute complex, physically viable dexterous behaviors without human demonstrations. More information at https://robin-lab.cs.utexas.edu/CoDex/.

Robotics0 citations2026-06-26arXiv ->

Drifting in the Future: Stabilizing Path Following Drifting on High-Latency Vehicle Systems

Frederik Werner, Till Heintzenberg, Markus Lienkamp, Johannes Betz

Autonomously controlling and handling a vehicle at and beyond its stability limit is a mathematically and computationally demanding task. Prior demonstrations of automated drifting have been limited to research platforms with instantaneous torque delivery and independently actuated wheels, leaving their applicability to production vehicles with actuator latencies and mechanically coupled axles uncertain. To overcome these issues, we design a predictor to compensate for powertrain delays, develop a revised control formulation to accommodate higher actuation latencies as well as a differential coupling on the driven axle, and introduce brake-based velocity stabilization. This paper presents the controller framework, the model extensions, and real-world experimental results. We observe that our controller enables a production sports car with a combustion engine to robustly sustain circular and figure-eight drifts, limiting lateral error to 1.1 m and sideslip overshoot to 0.06 rad despite actuator delays exceeding 250 ms, while mitigating oscillations and maintaining stable path and sideslip tracking. In conclusion, our results establish that autonomous drifting is feasible on production-ready vehicles, opening pathways to advanced safety systems capable of stabilizing cars in scenarios where traditional control fails.

MPC/Planning0 citations2026-06-25arXiv ->

Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)

Ilia Larchenko

I describe my solution to the LeHome Challenge 2026, an ICRA 2026 competition on bimanual garment folding. The system placed 1st of 62 teams in the online (simulation) round and 2nd in the real-world final. It improves a vision-language-action (VLA) policy with a reinforcement-learning loop. The policy is its own value function: the same network that predicts actions also predicts success, progress, and a few task-relevant future quantities, and those predictions drive advantage estimation, live failure detection, and candidate selection. The work mostly recombines existing RL ideas with engineering and optimization contributions that can be used together as one recipe or individually: AWR + RECAP combined for flow-matching VLA; an asynchronous distributed training / rollout pipeline through HuggingFace Hub; inference-time hyperparameters optimization via Thompson sampling; a sim-to-real recipe with camera-alignment tooling, heavy augmentation and DAgger-like HIL data collection.

Robotics0 citations2026-06-23arXiv ->

SurveilNav: Collaborative Object Goal Navigation with Robot and Surveillance System

Ming-Ming Yu, Qunbo Wang, Rongtao Xu, Yanghong Mei, Yirong Yang et al.

With the growing deployment of surveillance systems in factories, offices, and homes, integrating them with robots offers a promising direction for collaborative and efficient task execution. However, existing approaches largely focus on single-robot scenarios and struggle with multi-view collaboration in large-scale environments. In this paper, we present a novel indoor collaborative object navigation dataset built on Habitat-Sim, featuring 206 cameras across 74 floors. The dataset enables systematic evaluation of an agent's ability to exploit multi-view surveillance information. To address the limitations of single-robot perception, we propose SurveilNav, a collaborative navigation framework that integrates active camera scheduling, joint 2D/3D mapping, VLM-based value estimation, and collaborative target verification. By synergizing the robot's dynamic local perception with the static global view of surveillance, this architecture effectively overcomes both the limited perception range of single agents and the inherent blind spots of fixed cameras, resolving inefficient exploration. Experimental results on the HM3D dataset demonstrate that SurveilNav substantially outperforms existing methods, achieving state-of-the-art performance in both exploration efficiency and navigation success rate. Moreover, the system shows strong potential for applications in large-scale search, home environments, and rescue missions.

Robotics0 citations2026-06-23arXiv ->

Pocket-SLAM: Rendering-Area-Aware Pruning for Memory-Efficient 3DGS-SLAM

Leshu Li, Jie Peng, Yang Zhao

3D Gaussian Splatting (3DGS) has garnered significant attention in Simultaneous Localization and Mapping (SLAM) due to its advances in capturing fine-grained geometry features and synthesizing novel views. For SLAM in large-scale scenes, such as autonomous driving, 3DGS-SLAM faces a critical limitation: memory consumption increases continuously over time as Gaussian points accumulate, leading to poor memory efficiency and limiting its applicability. In this work, we propose a rendering-area-aware pruning strategy that selectively removes Gaussians based on their contribution to the effective rendering area, rather than solely relying on Gaussian-level heuristics such as opacity or gradient magnitude. This perspective directly targets the sources of memory redundancy, effectively reducing the peak memory footprint of 3DGS-SLAM during runtime. Evaluations on the EuRoC and KITTI datasets demonstrate that our method consistently outperforms existing pruning approaches in large-scale outdoor scenes, achieving over 60% memory reduction and more than 2 times FPS improvement while preserving localization and mapping accuracy. These results highlight rendering-area-aware pruning as a promising direction for scaling 3DGS-SLAM to real-world autonomous driving scenarios. Our code is publicly available at https://github.com/UMN-ZhaoLab/Pocket-SLAM.git.

Robotics0 citations2026-06-23arXiv ->

ArtiTwinSplat: Interactable Digital Twin Reconstruction via Gaussian Splatting from RGB-D videos

Pranjal Mishra, René Zurbrügg, Max Wilder-Smith, Marco Hutter, Marc Pollefeys et al.

Deploying robots in unstructured real-world environments needs accurate, interactive models of the objects. Constructing these models at scale remains a critical bottleneck for robotic system integration. We present ArtiTwinSplat, a framework that automatically constructs articulated, photo-realistic digital twins of objects directly from RGB-D videos, requiring no CAD models, simulation assets, or manual annotations. Our method is built on 3D Gaussian Splatting that preserve geometric fidelity and photometric realism, coupled with an unsupervised articulation discovery pipeline that recovers part structure and joint kinematics from observed motion alone. With tracking and optimization stages our method provides stable, queryable digital twins that support real-time rendering, viewpoint control, and interactive manipulation. Unlike prior methods confined to simulation, ArtiTwinSplat operates directly on real-world observations and produces twins that are immediately usable by downstream robot planning and learning systems. This method offers a practical, scalable pathway toward digital twin construction, lowering the integration barrier for articulated object manipulation in embodied AI and human-robot collaboration contexts.

Robotics0 citations2026-06-23arXiv ->

Explaining Failures of Cyber-Physical Systems with Actual Causality

Khen Elimelech, Tom Yaacov, David A. Kelly, Hana Chockler, Moshe Y. Vardi

Modern autonomous Cyber-Physical Systems (CPSs), such as self-driving cars, face increasingly complex demands, and yet are expected to act reliably. The black-box nature often characterizing such systems, especially those relying on neural components, makes it impossible to fully verify the system behavior prior to deployment. Unfortunately, unexpected failures-when the system does not comply with its specification-are inevitable and may have catastrophic implications. To improve trust in the system and facilitate future mitigation after a failure occurs, it is important to try to derive an explanation for the unexpected system behavior. This paper introduces the novel concept of leveraging the framework of actual causality for CPS failure explanation. Up until now, this framework was only used to derive explanations in the context of simple systems, such as image classifiers. This paper addresses the theoretical gaps and provides the guidance needed to allow for correct explanation derivation in the CPS domain. Beyond the theoretical contribution, the paper presents two novel, practical, system-agnostic explanation derivation algorithms, allowing to prioritize either explanation optimality or derivation efficiency. The approach is demonstrated and evaluated in the context of a neural-network-controlled autonomous car, designed to avoid collisions.

Robotics0 citations2026-06-22arXiv ->

Temporal Logic Guidance for Action-Only Diffusion Policies with World Models

Moritz Zoellner, Anastasios Manganaris, Rohan Paleja

Diffusion policies enable multimodal robot behavior but offer limited ability to choose among behavior modes at inference time, even though such control is desirable in human-robot settings. Prior solutions to this lack of control have utilized Signal Temporal Logic (STL) to express human intentions and provide corresponding guidance for diffusion policy inference. However, these approaches can only guide diffusion policies that jointly generate future actions and states, increasing both complexity and runtime. We propose a novel guidance method for action-only diffusion policies that uses a separate learned world model to enable differentiable evaluation of STL robustness, with its gradient then injected into the diffusion process. This steers behavior toward constraint satisfaction without retraining, improving constraint adherence while preserving task performance. On the Can Transport task from Robomimic, our method maintains 100% task success while reducing constraint violations from over 80% for baseline methods to 4%. We also discuss extensions toward improved robustness and more complex constraints.

Robotics0 citations2026-06-19arXiv ->

Technical Report for ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Exploring Query-Based Segmentation and Increased Spatial Context for Outdoor Scene Understanding

David Pascual-Hernández, Roberto Calvo-Palomino, Inmaculada Mora-Jiménez, Jose María Cañas-Plaza

In this report, we present our submission to the GOOSE 2D Fine-Grained Semantic Segmentation Challenge, organized as part of the Workshop on Field Robotics at ICRA 2026. The challenge combines data from the GOOSE and GOOSE-Ex datasets, which comprise more than 13k images captured from 4 distinct camera setups, annotated using a hierarchical taxonomy of 56 fine-grained classes and 11 broader categories. Starting from SegFormer as a baseline, we progressively improve segmentation performance through increased training crop sizes, a transition to the query-based Mask2Former architecture, and test-time augmentation. Our experiments show that query-based segmentation significantly outperforms the baseline model. Furthermore, increasing the crop size used during training yields substantial gains, highlighting the relevance of preserving scene context for fine-grained semantic disambiguation. Our final submission, using test-time augmentation, achieves an mIoU of 69.6% on the challenge test set, providing a strong baseline for fine-grained semantic segmentation in outdoor environments. To facilitate reproducibility and future research, code and weights will be made publicly available at https://github.com/RoboticsLabURJC/outdoor-fine-grained-segmentation .

Robotics0 citations2026-06-19arXiv ->

Overcoming Imperfect Kinematics in Surgical Robotics Through Sim-to-Real Visuomotor Learning

Zhaoxuan Yan, Kaizhong Deng, Zhaoyang Jacopo Hu, George P. Mylonas, Daniel S. Elson

Robot-Assisted Surgery is integral to modern minimally invasive procedures, with automation emerging as the next frontier to enhance precision and reduce surgeon fatigue. This evolution is largely impeded by the inherent kinematic inaccuracies of surgical robots, where unreliable internal sensors lead to significant control errors. While previous methods attempted to mitigate these issues through complex model-based calibration, they often suffer from high cost and limited effectiveness. This work utilises a learning-policy to actively compensate for hardware inaccuracies using closed-loop visual feedback that was trained from a teacher-student learning framework. The policy can fuse unreliable internal readings with precise external visual data, allowing it to correct for kinematic errors in real time without needing a perfect physical model. The learned policy was successfully deployed on the da Vinci Research Kit, where experiments validated the fundamental feasibility of using external vision to overcome internal sensor deficits. This research provides a foundational and reliable control methodology, paving the way for more advanced and robust surgical automation.

MPC/Planning0 citations2026-06-18arXiv ->

MMD-SLAM: Structure-Enhanced Multi-Meta Gaussian Distribution-Guided Visual SLAM

Fan Zhu, Ziyu Chen, Peichen Liu, Yifan Zhao, Zhisong Xu et al.

3D Gaussian Splatting (3DGS) has significantly boosted novel view synthesis and high-fidelity scene reconstruction, expanding the potential of 3DGS-based Visual Simultaneous Localization and Mapping (SLAM) methods. However, most existing systems fail to fully exploit the underlying structural information, which limits rendering quality and often leads to inconsistent maps. To address these limitations, we propose MMD-SLAM, a structure-enhanced Visual SLAM framework that leverages the Atlanta World (AW) assumption to guide a Multi-Meta Gaussian representation for photorealistic mapping. First, we introduce a point-line fusion strategy for pose optimization, where 3D line segments are incorporated to improve tracking robustness and provide additional constraints for mapping. Second, we design a Multi-Meta Gaussian representation with dominant directions, explicitly encoding structural priors from the AW hypothesis. Finally, we propose a Gaussian evolution strategy that adapts to scene geometry and incorporates structural cues into global optimization. Extensive experiments demonstrate that these innovations enable MMD-SLAM to achieve state-of-the-art performance in both tracking accuracy and mapping quality. e.g., our method achieves a 48.56% reduction in ATE RMSE on ScanNet and a 5.71% improvement in PSNR on Replica, compared with MonoGS.

MPC/Planning0 citations2026-06-18arXiv ->

Route-Constrained Robust Fusion Estimation for MEMS/GNSS Integrated Navigation of Unmanned Ground Vehicles in GNSS Degraded Environments

Jingzhi Cui, Chao Zhang, Yuliang Mao, Shaolin Lü, Dongmei Li et al.

To address cumulative localization drift of unmanned ground vehicles in structured road environments under severe Global Navigation Satellite System signal occlusion, this paper proposes a robust route-constrained state estimation method. During periods without satellite signals, the proposed method establishes the correspondence between the historical dead reckoning trajectory and local segments of the mission route extracted from a high-definition map, and estimates a route-referenced position via a two-dimensional rigid transformation. The estimated position is then formulated as a pseudo-position observation and incorporated into an Extended Kalman Filter update. In this way, route constraints at the road level can be continuously injected into a unified state estimation framework, thereby suppressing position deviation relative to the mission route while indirectly improving azimuth estimation. To enhance practical applicability, engineering strategies, such as trigger control, matching quality validation, route offset compensation, and single update correction limiting, are further introduced. Experiments in three representative scenarios, including a long tunnel, a multi-segment tunnel, and a curved tunnel, show that the proposed method effectively suppresses error accumulation during satellite outages, reduces the risk of large maximum deviation, and improves localization continuity and road-level usability.

Robotics0 citations2026-06-17arXiv ->

Learning to Annotate Delayed and False AEB Events: A Practical System for Extreme Class Imbalance and Asymmetric Label Noise

Mengxiang Hao, Xin Jiang, Xinghao Huang, Wenliang Su, Zhiteng Wang et al.

Autonomous Emergency Braking (AEB) optimization relies on accurately annotated real-world trigger events, particularly rare but critical delayed and false AEB triggers that expose system deficiencies. However, these minority samples comprise less than 5% of thousands of daily triggers, making manual annotation prohibitively expensive at scale. We present the first automated AEB annotation framework to address this problem. During development, we identified two fundamental challenges that severely impair delayed/false trigger annotation accuracy: (1) Extreme class imbalance where delayed/false triggers are overwhelmed by true triggers; (2) Asymmetric label noise where mislabeled majority samples (true triggers) suppress minority samples (delayed/false triggers) learning. To overcome these challenges, we propose two key innovations: (1) Specific data augmentation that synthesizes realistic samples by manipulating focal target attributes, transplanting ego-vehicle dynamics, and masking non-focal agents; (2) noise suppression using stable hardness estimation and probe-guided adaptive threshold to clean mislabeled true trigger samples. Crucially, we deploy our model as a practical annotation system with full-stack architecture, efficiently identifying critical delayed/false triggers from thousands of daily AEB events. Production results demonstrate 80% improvement in recall of delayed/false triggers and 50% reduction in manual workload. Beyond immediate gains, the system enables continuous self-improvement through accumulated high-quality annotations, establishing a necessary data foundation for on-vehicle AEB system optimization

Other0 citations2026-06-17arXiv ->

Spatially Stratified Distillation for Heterogeneous Radar Place Recognition

Sagun Singh Shrestha, Samuel Harding, Abdelwahed Khamis, Saimunur Rahman, Peyman Moghadam

Scalable, all-weather place recognition increasingly relies on heterogeneous radar place recognition to bridge diverse hardware platforms. A notable application is matching queries from cost-effective 4D automotive radars against high-fidelity reference maps built by dense spinning radars. This process is fundamentally limited by the extreme sparsity (and narrow field-of-view) of the 4D sensor, which captures only a fraction of the structural density present in the spinning radar database. Prior efforts address this issue by unifying different radar signals. That is, projecting both signals into a common representational space. Yet, they suffer performance degradation in multi-session environments. In this paper, we propose spatially-stratified distillation (SSD); a strategy that replaces standard uniform distillation with an asymmetric spatial alignment derived directly from physical radar returns. In regions where both radars exhibit overlapping returns, SSD enforces strong feature alignment. Crucially, in sparse regions where the 4D student lacks returns but the teacher contains valid structure within the shared field of view, SSD applies heavily discounted distillation weights. Extensive evaluations of the recent HeRCULES dataset demonstrate that SSD significantly outperforms prior place recognition methods, achieving state-of-the-art results on its challenging dynamic sequences.

Robotics0 citations2026-06-17arXiv ->

Technical Report for ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Leveraging DINOv3 for Robust Outdoor Scene Understanding in Field Robotics

Jaeil Park, Hyobin Choi, Sangjin Lee, Hyungtae Lim, Sung-Hoon Yoon

The GOOSE 2D Fine-Grained Semantic Segmentation Challenge at the ICRA 2026 Workshop on Field Robotics evaluates dense semantic segmentation of off-road imagery over a fine-grained taxonomy of 64 classes and 11 evaluated non-void coarse categories. We present the first-place solution to this challenge. Our solution comprises two complementary improvements: (a) a network-level design that combines a self-supervised DINOv3 ViT-L/16 backbone, a ViT-Adapter, and a Mask2Former mask-classification decoder, together with a coarse-category auxiliary loss on the global [CLS] token; and (b) an inference-time aggregation strategy based on multi-scale and horizontal-flip test-time augmentation and an ensemble of the top three checkpoints selected using Codabench scores. Our method achieves an official composite score of 76.57%, consisting of 69.32% fine-class mIoU and 83.81% category-level mIoU, and ranks first on the final phase leaderboard: www.codabench.org/competitions/14257/#/results-tab.

Robotics0 citations2026-06-16arXiv ->

Real-World Deployment of Massively Parallel Sampling-Based MPC for Contact-Rich Manipulation

Magnus Dierking, Joao Carvalho, An Thai Le, Georgia Chalvatzaki, Jan Peters

Sampling-based Model Predictive Control (SMPC) is a promising strategy for contact-rich robotic manipulation, combining gradient-free optimization with massively parallel GPU simulation. Yet, most prior work relies on simplified dynamics or remains confined to simulation. We present an MPC framework that leverages JAX for large-scale parallelization and efficient computation, coupled with the high-fidelity MuJoCo MJX simulator, and deploy it on a Franka Research 3 executing the Push-T manipulation task through a complete real-to-sim-to-real pipeline. The MTP variant with structured global sampling outperforms unimodal baselines such as CEM, MPPI, and PS across tasks that require mode switching, both in simulation and on hardware. Furthermore, we evaluate online domain randomization within the MPC sample budget, showing that contact-initiation parameters yield interpretable adaptation signals, whereas global physics parameters provide feedback that is too weak for reliable exploitation at typical replanning frequencies. These findings highlight key challenges for sampling-based MPC in contact-rich manipulation-contact sensitivity, tight compute budgets, and the difficulty of obtaining informative domain-randomization signals in real time.

Other0 citations2026-06-15arXiv ->

CrossMaps: Confidence-Aware Open-Vocabulary Semantic Mapping for Rover Navigation

Jan-Niklas Klein, Sona Ghahremani, Christian Medeiros Adriano, Holger Giese

Rovers rely on perception to maintain spatial maps that encode both objects and sensor quality (e.g., range reliability, lighting artifacts, data density), guiding data fusion, embedding updates, and navigation under partial observability. To study these coupled perception-navigation processes, we present CrossMaps, a real-time confidence-aware open-vocabulary semantic mapping pipeline that constructs language-queryable maps from RGB-D data. Building on VLMaps-style approaches, CrossMaps integrates multi-scale CLIP embeddings with confidence-aware fusion and a dual-memory architecture consisting of Short-Term Memory (STM) and Long-Term Memory (LTM). The STM aggregates noisy visual observations using geometric, semantic, and temporal confidence cues, while confident and coherent cells are promoted to the LTM as persistent semantic landmarks. Designed for deployment with a Jetson Orin-powered UGV alongside SLAM, CrossMaps runs in real time and produces semantic heatmaps that can be queried with natural language to guide rover navigation.

Robotics0 citations2026-06-15arXiv ->

A Deployment Case Study in Robotic Apparel Automation: Digital Twin Integration, Interoperability, and Workforce Enablement

Gokul Narayanan, Abhiroop Ajith, Jonathan Zornow, Carlos Calle, Auralis Herrero Lugo et al.

Despite steady advances in flexible automation in sectors such as electronics and automotive manufacturing, apparel automation remains challenging because fabrics are deformable and difficult to manipulate with robots. This paper presents a deployment-oriented case study of a robotic sewing system for denim manufacturing, emphasizing the system-level integration required for practical adoption. At the engineering level, a digital thread module parses DXF production drawings into process parameters and executable robot trajectories, reducing manual programming effort and enabling rapid re-targeting across sewing operations. In parallel, a digital twin of the workcell is used during pre-deployment to validate reach and clearance, refine layout and sequencing, evaluate operator access, and assess cycle-time compatibility with upstream and downstream tasks, thereby reducing commissioning risk. At deployment, the system integrates a collaborative robot with conventional sewing equipment, welding, suction fixtures, and machine-level controllers through an interoperability layer. Runtime monitoring and verification, including seam monitoring, collision checking, and trajectory-level validation, improve robustness under environmental variability, while operator-facing training and guidance tools support setup, troubleshooting, and technology adoption. Two staged factory deployments on denim shorts, covering 2D pocket operations and 3D garment-shaping seams, show that digital-twin-based validation, digital-thread-driven task generation, interoperability, runtime verification, and operator training are important for scaling robotic apparel automation.

Theory0 citations2026-06-11arXiv ->

Visual Place Recognition in Forests with Depth-Aware Distillation

Walter Nedov, Saimunur Rahman, Kavindie Katuwandeniya, David Hall, Kaushik Roy et al.

Visual place recognition in natural forest environments remains challenging due to repetitive vegetation, weak structural cues, and significant appearance variation across traversals. To address this limitation, this paper proposes a lightweight depth-aware distillation framework that injects geometric cues into a DINOv2-based place recognition model, while maintaining its pre-trained descriptor space. Evaluated on the recent WildCross benchmark, the proposed approach yields gains over an appearance-only counterpart, providing robustness to appearance variations. These results demonstrate the importance of depth as a strong complementary modality for place recognition in natural environments and identify depth-aware distillation as a promising direction for more robust forest perception.

Robotics0 citations2026-06-10arXiv ->

Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation

Mehmet Turan Yardımcı

Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy. A natural design choice is whether to use a single (unified) critic that estimates the combined value of all objectives, or separate (dual) critics with disjoint reward signals. We present a controlled comparison on the Unitree G1 humanoid (23 active DoF) in NVIDIA Isaac Lab, training loco-manipulation policies through a sequential curriculum spanning 13 levels from stationary reaching to walking with variable-orientation targets. In standardized evaluation, dual-critic policies reach targets 3.5$\times$ faster (6.5 vs. 22.6 simulation steps), achieve 2$\times$ higher throughput (14.3 vs. 7.0 validated reaches per 1,000 steps), and attain higher validated reach rates (65.2% vs. 53.8%) compared to the unified-critic policy. Notably, additional anti-gaming reward mechanisms provide no further improvement beyond the architectural change alone (60.9% vs. 65.2%). These results have direct implications for the emerging paradigm of RL fine-tuning of imitation-learned policies: when refining a pre-trained manipulation policy with RL, a unified critic risks suppressing the learned behavior through competing locomotion gradients. These findings demonstrate that critic architecture is a primary - and often overlooked - design choice in multi-objective humanoid RL, with greater impact than reward engineering on reaching efficiency.

Robotics0 citations2026-06-10arXiv ->

Cross-Modal Benchmarking for Robotic Perception in Natural Environments

David Hall, Joshua Knights, Mark Cox, Peyman Moghadam

Natural environments present a complex challenge to robotics perception systems. Current models, particularly vision foundation models, are largely trained on structured, urban environments leading to weaknesses in their perception for field robotics tasks. We showcase the limitations of current models using our recently released WildCross benchmark, a new cross-modal benchmark for place recognition and metric depth estimation in large-scale natural environments. WildCross comprises over 476K sequential RGB frames with semi-dense depth and surface normal annotations, each aligned with accurate 6DoF pose and synchronized dense lidar submaps. In this work, we provide an expanded analysis of the benchmark results from the recent WildCross benchmark, with particular emphasis on expanded metric depth estimation experiments. Access to the code repository and dataset for this work can be found at https://csiro-robotics.github.io/WildCross.

Robotics0 citations2026-06-09arXiv ->

Planar-Sector LOS Guidance for Interception of Agile Targets with Lifting-Wing Quadcopters

Linkai Liu, Kun Yang, Han Zou, Chen Min, Shuli Lv et al.

Autonomous visual interception of agile aerial targets is challenging due to unpredictable target motion, limited sensing, and the strong coupling between target visibility and interceptor maneuverability. Most existing strapdown-camera interception methods preserve visibility using conic line-of-sight (LOS) constraints that keep the target near the image center. While safe, such symmetric constraints unnecessarily restrict maneuverability and can significantly reduce the usable thrust for pursuit. Motivated by the observation that aggressive FPV pilots do not maintain equal visibility margins in all image directions, this paper proposes a Planar-Sector Line-of-Sight (PS-LOS) guidance framework for autonomous interception using a lifting-wing quadcopter equipped with only a strapdown monocular camera. PS-LOS tightly constrains lateral image error while relaxing longitudinal image error within a safe field-of-view margin, preserving visibility while releasing maneuverability for acceleration-intensive pursuit. Under the lifting-wing quadcopter model, PS-LOS provides nearly 50% more available thrust near the LOS direction than conventional conic LOS constraints. To realize LOS-only interception without direct depth measurements, a delay-compensated state-estimation framework and a nonlinear guidance-and-control architecture are developed for lifting-wing quadcopters. Extensive outdoor flight experiments demonstrate autonomous interception of agile targets exhibiting large-amplitude, high-frequency, and unpredictable motion under real wind disturbances. The proposed system achieves successful interceptions at ranges up to 138 m while maintaining continuous visual tracking throughout the engagement. The results validate PS-LOS as a visibility-preserving, maneuverability-aware guidance framework for long-range visual interception of agile aerial targets.

Robotics0 citations2026-06-08arXiv ->

Bayesian Optimization for Learning Nonlinear MPC in Autonomous Agent Navigation

Lorenzo Ortolani, Gabriel Voss, Gabriele Beltrami, Francesco Dorati, Tommaso Felice Banfi

Real-time autonomous navigation in dynamic, unknown environments remains a fundamental challenge for mobile robotics. We propose a map-free framework that tightly integrates reactive rolling-horizon planning with nonlinear Model Predictive Control (MPC). At each control cycle, a LiDAR-based Gaussian occupancy representation is constructed and used to generate collision-free trajectories via A* search, which are then tracked by a CasADi/IPOPT MPC formulation incorporating a smooth sigmoid obstacle barrier. To improve robustness to parameter sensitivity, we adopt an offline Bayesian optimization scheme based on Tree-structured Parzen Estimators (TPE), which identifies near-optimal controller parameters with respect to a composite navigation objective. In addition, a Gaussian Process surrogate is used to analyze parameter sensitivity and provide insight into the optimization landscape. The proposed framework is robot-agnostic and is evaluated on the Unitree Go2 quadruped in simulation using Gazebo, followed by deployment on the physical robot. Experimental results show that parameters tuned in simulation transfer effectively to hardware, maintaining comparable performance without additional tuning. The full system achieves up to a 90.0\% navigation success rate when deployed, along with a 38.9\% average improvement in the evaluation metrics across simulated environments.

Robotics0 citations2026-06-08arXiv ->

Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation

Luca Ghisi, Jacopo Essenziale, Carlo D'Eramo, Matteo Luperto

Autonomous Racing has seen remarkable progress through deep Reinforcement Learning (RL), primarily for four-wheeled vehicles. However, motorbikes introduce substantially greater complexity due to the need to manage balance and lean angle, in addition to more reactive steering and throttle control, and a smaller weight. In this work, we present a framework for training an autonomous agent to race a superbike in VRider SBK, a physics-accurate Unity-based motorbike simulator. Our approach integrates Soft Actor-Critic (SAC) with Self-Paced curriculum Deep reinforcement Learning (SPDL), which dynamically generates progressively more challenging tasks based on the agent's performance, without requiring manual curriculum design. The agent's state space comprises proprioceptive features extended with lean-angle history, along with global track features via course points. The reward signal is shaped to encourage progress along the track while penalizing instability-inducing behaviors specific to two-wheeled dynamics. Preliminary experimental results demonstrate that SPDL outperforms SAC alone in training efficiency, lap time, and driving stability across multiple tracks and motorbike models, establishing a first baseline for RL-based autonomous motorbike racing.

Robotics0 citations2026-06-08arXiv ->

From USD Scenes to Knowledge Graphs: Zero-Shot Ontology Grounding with LLMs

Jiangtao Shuai, Zongxiong Chen, Manfred Hauswirth, Sonja Schimmler

Constructing knowledge graphs from 3D simulation scenes is essential for robot task reasoning, but the key bottleneck, grounding scene objects to formal ontology classes, still relies on manually curated dictionaries that are brittle and do not generalize across assets. We investigate whether large language models (LLMs) can automate this grounding step for Universal Scene Description (USD) scenes as a zero-shot, training-free alternative. On a kitchen scene (125 objects) with SOMA-HOME Ontology, LLMs achieve 90-96% exact-match accuracy with descriptive names and 49-89% with abbreviated names, substantially outperforming dictionary and embedding baselines. Under fully opaque names, context-augmented prompting recovers up to 48%. Feature ablation reveals that LLMs primarily exploit semantic cues in the scene graph (sibling names and parent paths); anonymizing these cues reduces accuracy to 0-6%, while geometry alone yields only 4-17%.

CDC 2026 | 12 papers
CBF Related Papers
Theory0 citations2026-06-19arXiv ->

Conflict-Aware Switching for CBF-CLF-Based Multi-Goal Navigation

Rohan Walia, Kevin Leahy

Quadratic programs (QPs) using Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs) are widely used for safe control in reach-and-avoid navigation. However, the inherently conflicting nature of CBF and CLF constraints can lead to performance degradation, including slowdowns and deadlocks. This issue is exacerbated in multi-goal scenarios, where multiple nominal control objectives must be satisfied under shared safety constraints. Existing approaches for preemptive safety are often computationally expensive or overly conservative, while methods that relax or switch between nominal objectives are not well-suited for sequential goal-to-goal navigation. To address these limitations, we propose a conflict-aware switching strategy that detects high-conflict conditions and switches between available nominal control objectives to reduce constraint conflict. We apply this approach to multi-agent, multi-goal reach-and-avoid scenarios under CBF-CLF-QP control. Compared to a baseline sequential goal traversal strategy, our method reduces both completion time and timeout rates, demonstrating improved performance in satisfying all nominal control objectives while respecting safety constraints.

Robotics0 citations2026-04-16arXiv ->

CBF-based Probabilistic Safe Navigation under Unknown Nonlinear Obstacle Dynamics

Jiwon Lee, Hugo Matias, Daniel Silvestre, Thinh T. Doan

Safe navigation for an ego vehicle in uncertain environments characterized by dynamic obstacles with unknown nonlinear dynamics is a challenging problem of significant practical interest. Existing approaches in the literature either lack formal safety guarantees, require full model knowledge, or fail to account for the risk associated with the vehicle's exact body geometry and the temporal evolution of uncertainty between sampling instants. In this paper, we propose a data-driven observer for the unknown obstacle dynamics that generates an alpha-confidence set flow, which is exactly transformed into a Control Barrier Function (CBF) to enforce (1-alpha)-probability safety. The proposed framework accommodates nonlinear ego vehicle dynamics of arbitrary relative degree, as demonstrated through case studies involving first- and second-order dynamics of an unmanned surface vehicle.

MPC/Planning0 citations2026-04-10arXiv ->

Probabilistic Control Barrier Functions for Systems with State Estimation Uncertainty using Sub-Gaussian Concentration

Kazuya Echigo, David E. J. van Wijk, Pol Mestres, Ersin Daş, Joel W. Burdick et al.

Safety-critical control systems, such as spacecraft performing proximity operations, must provide formal safety guarantees despite stochastic uncertainties from state estimation and unmodeled dynamics. Although Control Barrier Functions (CBFs) have been extended to stochastic systems, existing approaches typically face a trade-off between the tightness of probabilistic guarantees and computational tractability. This paper presents a particle-based probabilistic CBF framework that overcomes this limitation by exploiting the sub-Gaussian structure of the barrier function increment under Gaussian uncertainties. We establish that Gaussian uncertainties propagating through Lipschitz-continuous control-affine dynamics preserve sub-Gaussianity of the barrier function increment, with explicit tail bounds. Leveraging this structure, we derive finite-sample bounds on the approximation error between particle-based Conditional Value at Risk (CVaR) estimates and ground-truth probabilistic constraints; applying this yields a tractable optimization problem formulation with finite-sample safety certificates. We show through numerical experiments how the proposed approach provides tight yet provably valid probabilistic safety guarantees.

Other0 citations2026-04-04arXiv ->

SafeSpace: Aggregating Safe Sets from Backup Control Barrier Functions under Input Constraints

Pio Ong, David E. J. van Wijk, Massimiliano de Sa, Joel W. Burdick, Aaron D. Ames

Control barrier functions (CBFs) provide a principled framework for enforcing safety in control systems -- yet the certified safe operating region in practice is often conservative, especially under input bounds. In many applications, multiple smaller safe sets can be certified independently, e.g., around distinct equilibria with different stabilizing controllers. This paper proposes a framework for uniting such regions into a single certified safe set using \emph{combinatorial CBFs}. We refine the combinatorial CBF framework by introducing an auxiliary variable that enables logical compositions of individual CBFs. In the proposed framework, we show that such compositions yield a \emph{generalized combinatorial CBF} under a condition termed \emph{conjunctive compatibility}. Building on this result, we extend the framework to enable the aggregation of multiple implicit safe sets generated by the backup CBF framework. We show that the resulting CBF-based quadratic program yields a continuous safety filter over the aggregated safe region. The approach is demonstrated on two spacecraft safety problems, safe attitude control and safe station keeping, where multiple certified safe regions are combined to expand the operational envelope.

MPC/Planning0 citations2026-04-01arXiv ->

Tube-Based Safety for Anticipative Tracking in Multi-Agent Systems

Armel Koulong, Ali Pakniyat

A tube-based safety framework is presented for robust anticipative tracking in nonlinear Brunovsky multi-agent systems subject to bounded disturbances. The architecture establishes robust safety certificates for a feedforward-augmented ancillary control policy. By rendering the state-deviation dynamics independent of the agents' internal nonlinearities, the formulation strictly circumvents the restrictive Lipschitz-bound feasibility conditions otherwise required for robust stabilization. Consequently, this structure admits an explicit, closed-form robust positively invariant (RPI) tube radius that systematically attenuates the exponential control barrier function (eCBF) tightening margins, thereby mitigating constraint conservatism while preserving formal forward invariance. Within the distributed model predictive control (MPC) layer, mapping the local tube radii through the communication graph yields a closed-form global formation error bound formulated via the minimum singular value of the augmented Laplacian. Robust inter-agent safety is enforced with minimal communication overhead, requiring only a single scalar broadcast per neighbor at initialization. Numerical simulations confirm the framework's efficacy in safely navigating heterogeneous formations through cluttered environments.

Other Papers
Robotics0 citations2026-07-21arXiv ->

Stochastic Multi-Objective Kinodynamic Planning Against Adversaries

Thomas Marshall Vielmetti, Daniel Cherenson, Dimitra Panagou

This paper addresses multi-objective kinodynamic planning in environments with stochastic hybrid adversaries that probabilistically transition to adversarial modes based on the ego state. The goal is to construct the Pareto-front of paths that trade off execution cost and the probability of safety constraint violation (risk). Existing chance-constrained planners evaluate risk over open-loop trajectories, yielding overly conservative solutions that fail to account for ego-agent reactivity. To address this limitation, we shift the planning space to sequences of closed-loop policies, and integrate sample-based risk evaluation directly into tree construction via Monte-Carlo particle rollouts. We first introduce Stochastic Multi-Objective RRT (SMO-RRT), for which we prove probabilistic completeness, followed by Stochastic Multi-Objective Stable Sparse RRT (SMO-SST), which leverages selective pruning to improve numerical performance at the cost of completeness. For both algorithms, we derive a finite-sample bound on the probability of chance constraint violation for systems with non-Gaussian, state-dependent uncertainty, enabling probabilistically safe planning in a broad class of environments applicable to multi-agent systems, social navigation, and autonomous driving.

Robotics0 citations2026-04-17arXiv ->

Verification of Autonomous Systems with Optimal Controllers

Dylan Le, Joel McCandless, Carlos Varela, Radoslav Ivanov

This paper considers the problem of reachability analysis of control systems with optimal controllers, as a first step towards verifying the safety and correctness of such systems. Despite their appeal in guaranteeing task satisfaction through cost minimization, optimal controllers are often challenging to assure. In particular, as system dynamics grow in complexity, solving the resulting optimization problem may be difficult, especially given time and computation constraints on real platforms. Thus, it is essential to verify that, even if the optimal solution is not always found, such controllers still accomplish the high-level control objective. In this paper, we focus on gradient descent algorithms and design a reachability algorithm by treating gradient descent as a separate (digital) dynamical system, embedded in the original (physical) dynamical system, with controls as part of the state. We evaluate the feasibility of the proposed method on two control systems, a two-dimensional quadrotor and a cartpole.

Robotics0 citations2026-04-10arXiv ->

Decentralized Opinion-Integrated Decision making at Unsignalized Intersections via Signed Networks

Bhaskar Varma, Ying Shuai Quan, Karl D. von Ellenrieder, Paolo Falcone

In this letter, we consider the problem of decentralized decision making among connected autonomous vehicles at unsignalized intersections, where existing centralized approaches do not scale gracefully under mixed maneuver intentions and coordinator failure. We propose a closed-loop opinion-dynamic decision model for intersection coordination, where vehicles exchange intent through dual signed networks: a conflict topology based communication network and a commitment-driven belief network that enable cooperation without a centralized coordinator. Continuous opinion states modulate velocity optimizer weights prior to commitment; a closed-form predictive feasibility gate then freezes each vehicle's decision into a GO or YIELD commitment, which propagates back through the belief network to pre-condition neighbor behavior ahead of physical conflicts. Crossing order emerges from geometric feasibility and arrival priority without the use of joint optimization or a solver. The approach is validated across three scenarios spanning fully competitive, merge, and mixed conflict topologies. The results demonstrate collision-free coordination and lower last-vehicle exit times compared to first come first served (FCFS) in all conflict non-trivial configurations.

Theory0 citations2026-04-09arXiv ->

Complementary Filtering on SO(3) for Attitude Estimation with Scalar Measurements

Alessandro Melis, Soulaimane Berkane, Tarek Hamel

Attitude estimation using scalar measurements, corresponding to partial vectorial observations, arises naturally when inertial vectors are not fully observed but only measured along specific body-frame vectors. Such measurements arise in problems involving incomplete vector measurements or attitude constraints derived from heterogeneous sensor information. Building on the classical complementary filter on SO(3), we propose an observer with a modified innovation term tailored to this scalar-output structure. The main result shows that almost-global asymptotic stability is recovered, under suitable persistence of excitation conditions, when at least three inertial vectors are measured along a common body-frame vector, which is consistent with the three-dimensional structure of SO(3). For two-scalar configurations - corresponding either to one inertial vector measured along two body-frame vectors, or to two inertial vectors measured along a common body-frame vector - we further derive sufficient conditions guaranteeing convergence within a reduced basin of attraction. Different examples and numerical results demonstrate the effectiveness of the proposed scalar-based complementary filter for attitude estimation in challenging scenarios involving reduced sensing and/or novel sensing modalities.

MPC/Planning0 citations2026-04-07arXiv ->

Staggered Integral Online Conformal Prediction for Safe Dynamics Adaptation with Multi-Step Coverage Guarantees

Daniel M. Cherenson, Dimitra Panagou

Safety-critical control of uncertain, adaptive systems often relies on conservative, worst-case uncertainty bounds that limit closed-loop performance. Online conformal prediction is a powerful data-driven method for quantifying uncertainty when truth values of predicted outputs are revealed online; however, for systems that adapt the dynamics without measurements of the state derivatives, standard online conformal prediction is insufficient to quantify the model uncertainty. We propose Staggered Integral Online Conformal Prediction (SI-OCP), an algorithm utilizing an integral score function to quantify the lumped effect of disturbance and learning error. This approach provides long-run coverage guarantees, resulting in long-run safety when synthesized with safety-critical controllers, including robust tube model predictive control. Finally, we validate the proposed approach through a numerical simulation of an all-layer deep neural network (DNN) adaptive quadcopter using robust tube MPC, highlighting the applicability of our method to complex learning parameterizations and control strategies.

Robotics0 citations2026-04-06arXiv ->

Synchronous Observer Design for Landmark-Inertial SLAM with Magnetometer and Intermittent GNSS Measurements

Arkadeep Saha, Pieter van Goor, Ravi Banavar

In Landmark-Inertial Simultaneous Localisation and Mapping (LI-SLAM), the positions of landmarks in the environment and the robot's pose relative to these landmarks are estimated using landmark position measurements, and measurements from the Inertial Measurement Unit (IMU). However, the robot and landmark positions in the inertial frame, and the yaw of the robot, are not observable in LI-SLAM. This paper proposes a nonlinear observer for LI-SLAM that overcomes the observability constraints with the addition of intermittent GNSS position and magnetometer measurements. The full-state error dynamics of the proposed observer is shown to be both almost-globally asymptotically stable and locally exponentially stable, and this is validated using simulations.

Robotics0 citations2026-04-06arXiv ->

Constraint-Induced Redistribution of Social Influence in Nonlinear Opinion Dynamics

Vishnudatta Thota, Anastasia Bizyaeva

We study how intrinsic hard constraints on the decision dynamics of social agents shape collective decisions on multiple alternatives in a heterogeneous group. Such constraints may arise due to structural and behavioral limitations, such as adherence to belief systems in social networks or hardware limitations in autonomous networks. In this work, agent constraints are encoded as projections in a multi-alternative nonlinear opinion dynamics framework. We prove that projections induce an invariant subspace on which the constraints are always satisfied and study the dynamics of networked opinions on this subspace. We then show that heterogeneous pairwise alignments between individuals' constraint vectors generate an effective weighted social graph on the invariant subspace, even when agents exchange opinions over an unweighted communication graph in practice. With analysis and simulation studies, we illustrate how the effective constraint-induced weighted graph reshapes the centrality of agents in the decision process and the group's sensitivity to distributed inputs.

CDC 2025 | 10 papers
CBF Related Papers
Robotics0 citations2025-12-01arXiv ->

Dynamic Log-Gaussian Process Control Barrier Function for Safe Robotic Navigation in Dynamic Environments

Xin Yin, Chenyang Liang, Yanning Guo, Jie Mei

Control Barrier Functions (CBFs) have emerged as efficient tools to address the safe navigation problem for robot applications. However, synthesizing informative and obstacle motion-aware CBFs online using real-time sensor data remains challenging, particularly in unknown and dynamic scenarios. Motived by this challenge, this paper aims to propose a novel Gaussian Process-based formulation of CBF, termed the Dynamic Log Gaussian Process Control Barrier Function (DLGP-CBF), to enable real-time construction of CBF which are both spatially informative and responsive to obstacle motion. Firstly, the DLGP-CBF leverages a logarithmic transformation of GP regression to generate smooth and informative barrier values and gradients, even in sparse-data regions. Secondly, by explicitly modeling the DLGP-CBF as a function of obstacle positions, the derived safety constraint integrates predicted obstacle velocities, allowing the controller to proactively respond to dynamic obstacles' motion. Simulation results demonstrate significant improvements in obstacle avoidance performance, including increased safety margins, smoother trajectories, and enhanced responsiveness compared to baseline methods.

Robotics0 citations2025-09-18arXiv ->

A Nonlinear Scaling-based Design of Control Lyapunov-barrier Function for Relative Degree 2 Case and its Application to Safe Feedback Linearization

Haechan Pyon, Gyunghoon Park

In this paper we address the problem of control Lyapunov-barrier function (CLBF)-based safe stabilization for a class of nonlinear control-affine systems. A difficulty may arise for the case when a constraint has the relative degree larger than 1, at which computing a proper CLBF is not straightforward. Instead of adding an (possibly non-existent) control barrier function (CBF) to a control Lyapunov function (CLF), our key idea is to simply scale the value of the CLF on the unsafe set, by utilizing a sigmoid function as a scaling factor. We provide a systematic design method for the CLBF, with a detailed condition for the parameters of the sigmoid function to satisfy. It is also seen that the proposed approach to the CLBF design can be applied to the problem of task-space control for a planar robot manipulator with guaranteed safety, for which a safe feedback linearization-based controller is presented.

MPC/Planning0 citations2025-09-04arXiv ->

Compatibility of Multiple Control Barrier Functions for Constrained Nonlinear Systems

Max H. Cohen, Eugene Lavretsky, Aaron D. Ames

Control barrier functions (CBFs) are a powerful tool for the constrained control of nonlinear systems; however, the majority of results in the literature focus on systems subject to a single CBF constraint, making it challenging to synthesize provably safe controllers that handle multiple state constraints. This paper presents a framework for constrained control of nonlinear systems subject to box constraints on the systems' vector-valued outputs using multiple CBFs. Our results illustrate that when the output has a vector relative degree, the CBF constraints encoding these box constraints are compatible, and the resulting optimization-based controller is locally Lipschitz continuous and admits a closed-form expression. Additional results are presented to characterize the degradation of nominal tracking objectives in the presence of safety constraints. Simulations of a planar quadrotor are presented to demonstrate the efficacy of the proposed framework.

MPC/Planning0 citations2025-09-04arXiv ->

Sample Efficient Certification of Discrete-Time Control Barrier Functions

Sampath Kumar Mulagaleti, Andrea Del Prete

Control Invariant (CI) sets are instrumental in certifying the safety of dynamical systems. Control Barrier Functions (CBFs) are effective tools to compute such sets, since the zero sublevel sets of CBFs are CI sets. However, computing CBFs generally involves addressing a complex robust optimization problem, which can be intractable. Scenario-based methods have been proposed to simplify this computation. Then, one needs to verify if the CBF actually satisfies the robust constraints. We present an approach to perform this verification that relies on Lipschitz arguments, and forms the basis of a certification algorithm designed for sample efficiency. Through a numerical example, we validated the efficiency of the proposed procedure.

MPC/Planning0 citations2025-08-27arXiv ->

Distributed Safety-Critical MPC for Multi-Agent Formation Control and Obstacle Avoidance

Chao Wang, Shuyuan Zhang, Lei Wang

For nonlinear multi-agent systems with high relative degrees, achieving formation control and obstacle avoidance in a distributed manner remains a significant challenge. To address this issue, we propose a novel distributed safety-critical model predictive control (DSMPC) algorithm that incorporates discrete-time high-order control barrier functions (DHCBFs) to enforce safety constraints, alongside discrete-time control Lyapunov functions (DCLFs) to establish terminal constraints. To facilitate distributed implementation, we develop estimated neighbor states for formulating DHCBFs and DCLFs, while also devising a bound constraint to limit estimation errors and ensure convergence. Additionally, we provide theoretical guarantees regarding the feasibility and stability of the proposed DSMPC algorithm based on a mild assumption. The effectiveness of the proposed method is evidenced by the simulation results, demonstrating improved performance and reduced computation time compared to existing approaches.

Other Papers
Robotics0 citations2026-01-16arXiv ->

Adaptive Monitoring of Stochastic Fire Front Processes via Information-seeking Predictive Control

Savvas Papaioannou, Panayiotis Kolios, Christos G. Panayiotou, Marios M. Polycarpou

We consider the problem of adaptively monitoring a wildfire front using a mobile agent (e.g., a drone), whose trajectory determines where sensor data is collected and thus influences the accuracy of fire propagation estimation. This is a challenging problem, as the stochastic nature of wildfire evolution requires the seamless integration of sensing, estimation, and control, often treated separately in existing methods. State-of-the-art methods either impose linear-Gaussian assumptions to establish optimality or rely on approximations and heuristics, often without providing explicit performance guarantees. To address these limitations, we formulate the fire front monitoring task as a stochastic optimal control problem that integrates sensing, estimation, and control. We derive an optimal recursive Bayesian estimator for a class of stochastic nonlinear elliptical-growth fire front models. Subsequently, we transform the resulting nonlinear stochastic control problem into a finite-horizon Markov decision process and design an information-seeking predictive control law obtained via a lower confidence bound-based adaptive search algorithm with asymptotic convergence to the optimal policy.

Robotics0 citations2025-11-25arXiv ->

Energy Efficient Nonlinear Microscopic Dynamical Model for Autonomous and Electric Vehicles

Yuneil Yeo, Jaewoong Lee, Scott Moura, Maria Laura Delle Monache

This article proposes a nonlinear microscopic dynamical model for autonomous electric vehicles (A-EVs) that considers battery energy efficiency in the car-following dynamics. The model builds upon the Optimal Velocity Model (OVM), with the control term based on the battery dynamics to enable thermally optimal and energy-efficient driving. We rigorously prove that the proposed model achieves lower energy consumption compared to the Optimal Velocity Follow-the-Leader (OVFL) model. Through numerical simulations, we validate the analytical results on the energy efficiency. We additionally investigate the stability properties of the proposed model.

Robotics0 citations2025-11-19arXiv ->

Real-Time Optimal Control via Transformer Networks and Bernstein Polynomials

Gage MacLin, Venanzio Cichella, Andrew Patterson, Irene Gregory

In this paper, we propose a Transformer-based framework for approximating solutions to infinite-dimensional optimization problems: calculus of variations problems and optimal control problems. Our approach leverages offline training on data generated by solving a sample of infinite- dimensional optimization problems using composite Bernstein collocation. Once trained, the Transformer efficiently generates near-optimal, feasible trajectories, making it well-suited for real-time applications. In motion planning for autonomous vehicles, for instance, these trajectories can serve to warm- start optimal motion planners or undergo rigorous evaluation to ensure safety. We demonstrate the effectiveness of this method through numerical results on a classical control problem and an online obstacle avoidance task. This data-driven approach offers a promising solution for real-time optimal control of nonlinear, nonconvex systems.

Robotics0 citations2025-09-16arXiv ->

Ellipsoidal partitions for improved multi-stage robust model predictive control

Moritz Heinlein, Florian Messerer, Moritz Diehl, Sergio Lucia

Ellipsoidal tube-based model predictive control methods effectively account for the propagation of the reachable set, typically employing linear feedback policies. In contrast, scenario-based approaches offer more flexibility in the feedback structure by considering different control actions for different branches of a scenario tree. However, they face challenges in ensuring rigorous guarantees. This work aims to integrate the strengths of both methodologies by enhancing ellipsoidal tube-based MPC with a scenario tree formulation. The uncertainty ellipsoids are partitioned by halfspaces such that each partitioned set can be controlled independently. The proposed ellipsoidal multi-stage approach is demonstrated in a human-robot system, highlighting its advantages in handling uncertainty while maintaining computational tractability.

Learning0 citations2025-09-03arXiv ->

Population-aware Online Mirror Descent for Mean-Field Games with Common Noise by Deep Reinforcement Learning

Zida Wu, Mathieu Lauriere, Matthieu Geist, Olivier Pietquin, Ankur Mehta

Mean Field Games (MFGs) offer a powerful framework for studying large-scale multi-agent systems. Yet, learning Nash equilibria in MFGs remains a challenging problem, particularly when the initial distribution is unknown or when the population is subject to common noise. In this paper, we introduce an efficient deep reinforcement learning (DRL) algorithm designed to achieve population-dependent Nash equilibria without relying on averaging or historical sampling, inspired by Munchausen RL and Online Mirror Descent. The resulting policy is adaptable to various initial distributions and sources of common noise. Through numerical experiments on seven canonical examples, we demonstrate that our algorithm exhibits superior convergence properties compared to state-of-the-art algorithms, particularly a DRL version of Fictitious Play for population-dependent policies. The performance in the presence of common noise underscores the robustness and adaptability of our approach.

ACC 2026 | 23 papers
CBF Related Papers
Robotics0 citations2026-06-05arXiv ->

Verification Framework for the Union of Control Barrier Functions

Chuanrui Jiang, Andrew Clark

Control Barrier Functions (CBFs) have been proposed to ensure safety of autonomous systems. This paper considers control policies that switch between CBF constraints. Under this approach, we represent a complex non-convex safe region as a union of sets that are computationally tractable to verify. We denote this framework as union-CBFs and make the following contributions. First, considering switching CBF-QP controllers, we propose a sufficient condition that ensures (i) the system undergoes a finite number of switches in any finite time interval and ensures (ii) the forward invariance of the closed-loop system in between switches. Second, we consider two types of switching strategies and propose union-CBFs conditions for each strategy to satisfy (i) and (ii). Third, we formulate Sum-of-Squares (SOS) algorithms to verify the conditions. The experiments show that our union-CBFs framework results in a larger safe region compared to high-degree polynomial CBFs. We also show the efficiency of the verification algorithms using a polynomial system model.

MPC/Planning0 citations2026-04-06arXiv ->

Collaborative Altruistic Safety in Coupled Multi-Agent Systems

Brooks A. Butler, Xiao Tan, Aaron D. Ames, Magnus Egerstedt

This paper presents a novel framework for ensuring safety in dynamically coupled multi-agent systems through collaborative control. Drawing inspiration from ecological models of altruism, we develop collaborative control barrier functions that allow agents to cooperatively enforce individual safety constraints under coupling dynamics. We introduce an altruistic safety condition based on the so-called Hamilton's rule, enabling agents to trade off their own safety to support higher-priority neighbors. By incorporating these conditions into a distributed optimization framework, we demonstrate increased feasibility and robustness in maintaining system-wide safety. The effectiveness of the proposed approach is illustrated through simulation in a simplified formation control scenario.

Robotics0 citations2026-03-17arXiv ->

Shielded Reinforcement Learning Under Dynamic Temporal Logic Constraints

Sadık Bera Yüksel, Ali Tevfik Buyukkocak, Derya Aksaray

Reinforcement Learning (RL) has shown promise in various robotics applications, yet its deployment on real systems is still limited due to safety and operational constraints. The safe RL field has gained considerable attention in recent years, which focuses on imposing safety constraints throughout the learning process. However, real systems often require more complex constraints than just safety, such as periodic recharging or time-bounded visits to specific regions. Imposing such spatio-temporal tasks during learning still remains a challenge. Signal Temporal Logic (STL) is a formal language for specifying temporal properties of real-valued signals and provides a way to express such complex tasks. In this paper, we propose a framework that leverages sequential control barrier functions and model-free RL to ensure that the given STL tasks are satisfied throughout the learning process. Our method extends beyond traditional safety constraints by enforcing rich STL specifications, which can involve visits to dynamic targets with unknown trajectories. We also demonstrate the effectiveness of our framework through various simulations.

Theory0 citations2026-03-16arXiv ->

ReLU Barrier Functions for Nonlinear Systems with Constrained Control: A Union of Invariant Sets Approach

Pouya Samanipour, Hasan A. Poonawala

Certifying safety for nonlinear systems with polytopic input constraints is challenging because CBF synthesis must ensure control admissibility under saturation. We propose an approximation--verification pipeline that performs convex barrier synthesis on piecewise-affine (PWA) surrogates and certifies safety for the original nonlinear system via facet-wise verification. To reduce conservatism while preserving tractability, we use a two-slope Leaky ReLU surrogate for the extended class-$\mathcal{K}$ function $α(\cdot)$ and combine multiple certificates using a Union of Invariant Sets (UIS). Counterexamples are handled through local uncertainty updates. Simulations on pendulum and cart-pole systems with input saturation show larger certified invariant sets than linear-$α$ designs with tractable computation time.

Robotics0 citations2026-02-08arXiv ->

From Ellipsoids to Midair Control of Dynamic Hitches

Jiawei Xu, Subhrajit Bhattacharya, David Saldaña

The ability to manipulate and interlace cables using aerial vehicles can greatly improve aerial transportation tasks. Such interlacing cables create hitches by winding two or more cables around each other, which can enclose payloads or can further develop into knots. Dynamic modeling and control of such hitches are key to mastering inter-cable interactions in the context of cable-suspended aerial manipulation. This paper introduces an ellipsoid-based kinematic model to connect the geometric nature of a hitch created by two cables and the dynamics of the hitch driven by four aerial vehicles, which reveals the control-affine form of the system. As the constraint for maintaining tension of a cable is also control-affine, we design a quadratic programming-based controller that combines Control Lyapunov and High-Order Control Barrier Functions (CLF-HOCBF-QP) to precisely track a desired hitch position and system shape while enforcing safety constraints like cable tautness. We convert desired geometric reference configurations into target robot positions and introduce a composite error into the Lyapunov function to ensure a relative degree of one to the input. Numerical simulations validate our approach, demonstrating stable, high-speed tracking of dynamic references.

Other0 citations2026-02-04arXiv ->

Banach Control Barrier Functions for Large-Scale Swarm Control

Xuting Gao, Guillem Pascual, Scott Brown, Sonia Martínez

This paper studies the safe control of very large multi-agent systems via a generalized framework that employs so-called Banach Control Barrier Functions (B-CBFs). Modeling a large swarm as probability distribution over a spatial domain, we show how B-CBFs can be used to appropriately capture a variety of macroscopic constraints that can integrate with large-scale swarm objectives. Leveraging this framework, we define stable and filtered gradient flows for large swarms, paying special attention to optimal transport algorithms. Further, we show how to derive agent-level, microscopical algorithms that are consistent with macroscopic counterparts in the large-scale limit. We then identify conditions for which a group of agents can compute a distributed solution that only requires local information from other agents within a communication range. Finally, we showcase the theoretical results over swarm systems in the simulations section.

Other0 citations2026-02-04arXiv ->

Peak Bounds for the Estimation Error under Sensor Attacks

Axel Stafström, Daniel Arnström, Adam Miksits, David Umsonst

This paper investigates bounds on the estimation error of a linear system affected by norm-bounded disturbances and full sensor attacks. The system is equipped with a detector that evaluates the norm of the innovation signal to detect faults, and the attacker wants to avoid detection. We utilize induced $L_\infty$ system norms, also called \emph{peak-to-peak} norms, to compare the estimation error bounds under nominal operations and under attack. This leads to a sufficient condition for when the bound on the estimation error is smaller during an attack than during nominal operation. This condition is independent of the attack strategy and depends only on the attacker's desire to remain undetected and (indirectly) the observer gain. Therefore, we investigate both an observer design method, that seeks to reduce the error bound under attack while keeping the nominal error bound low, and detector threshold tuning. As a numerical illustration, we show how a sensor attack can deactivate a robust safety filter based on control barrier functions if the attacked error bound is larger than the nominal one. We also statistically evaluate our observer design method and the effect of the detector threshold.

Other0 citations2026-02-02arXiv ->

Robust Safety-Critical Control of Networked SIR Dynamics

Saba Samadi, Brooks A. Butler, Philip E. Paré

We present a robust safety-critical control framework tailored for networked susceptible-infected-recovered (SIR) epidemic dynamics, leveraging control barrier functions (CBFs) and robust control barrier functions to address the challenges of epidemic spread and mitigation. In our networked SIR model, each node must keep its infection level below a critical threshold, despite dynamic interactions with neighboring nodes and inherent uncertainties in the epidemic parameters and measurement errors, to ensure public health safety. We first derive a CBF-based controller that guarantees infection thresholds are not exceeded in the nominal case. We enhance the framework to handle realistic epidemic scenarios under uncertainties by incorporating compensation terms that reinforce safety against uncertainties: an independent method with constant bounds for uniform uncertainty, and a novel approach that scales with the state to capture increased relative noise in early or suppressed outbreak stages. Simulation results on a networked SIR system illustrate that the nominal CBF controller maintains safety under low uncertainty, while the robust approaches provide formal safety guarantees under higher uncertainties; in particular, the novel method employs more conservative control efforts to provide larger safety margins, whereas the independent approach optimizes resource allocation by allowing infection levels to approach the boundaries in steady epidemic regimes.

Robotics0 citations2025-10-23arXiv ->

From Bundles to Backstepping: Geometric Control Barrier Functions for Safety-Critical Control on Manifolds

Massimiliano de Sa, Pio Ong, Aaron D. Ames

Control barrier functions (CBFs) have a well-established theory in Euclidean spaces, yet still lack general formulations and constructive synthesis tools for systems evolving on manifolds common in robotics and aerospace applications. In this paper, we develop a general theory of geometric CBFs on bundles and, for control-affine systems, recover the standard optimization-based CBF controllers and their smooth analogues. Then, by generalizing kinetic energy-based CBF backstepping to Riemannian manifolds, we provide a constructive CBF synthesis technique for geometric mechanical systems, as well as easily verifiable conditions under which it succeeds. Further, this technique utilizes mechanical structure to avoid computations on higher-order tangent bundles. We demonstrate its application to an underactuated satellite on SO(3).

Robotics0 citations2025-10-15arXiv ->

Belief Space Control of Safety-Critical Systems Under State-Dependent Measurement Noise

Rohan Walia, Mitchell Black, Andrew Schoer, Kevin Leahy

Safety-critical control is imperative for deploying autonomous systems in the real world. Control Barrier Functions (CBFs) offer strong safety guarantees when accurate system and sensor models are available. However, widely used additive, fixed-noise models are not representative of complex sensor modalities with state-dependent error characteristics. Although CBFs have been designed to mitigate uncertainty using fixed worst-case bounds on measurement noise, this approach can lead to overly-conservative control. To solve this problem, we extend the Belief Control Barrier Function (BCBF) framework to accommodate state-dependent measurement noise via the Generalized Extended Kalman Filter (GEKF) algorithm, which models measurement noise as a linear function of the state. Using the original BCBF framework as baseline, we demonstrate the performance of the BCBF-GEKF approach through simulation results on a 1D single integrator setpoint tracking scenario and 2D unicycle kinematics trajectory tracking scenario. Our results confirm that the BCBF-GEKF approach offers less conservative control with greater safety.

Theory0 citations2025-10-08arXiv ->

Decentralized CBF-based Safety Filters for Collision Avoidance of Cooperative Missile Systems with Input Constraints

Johannes Autenrieb, Mark Spiller

This paper presents a decentralized safety filter for collision avoidance in multi-agent aerospace interception scenarios. The approach leverages robust control barrier functions (RCBFs) to guarantee forward invariance of safe sets under bounded inputs and high-relative-degree dynamics. Each effector executes its nominal cooperative guidance command, while a local quadratic program (QP) modifies the input only when necessary. Event-triggered activation based on range and zero-effort miss (ZEM) criteria ensures scalability by restricting active constraints to relevant neighbors. To ensure feasibility under multiple simultaneously active constraints, a slack-variable relaxation scheme is introduced that prioritizes critical agents in a Pareto-optimal manner. Simulation results in many-on-many interception scenarios demonstrate that the proposed framework maintains collision-free operation with minimal deviation from nominal guidance, providing a computationally efficient and scalable solution for safety-critical multi-agent aerospace systems.

Robotics0 citations2025-10-07arXiv ->

Safe Landing on Small Celestial Bodies with Gravitational Uncertainty Using Disturbance Estimation and Control Barrier Functions

Felipe Arenas-Uribe, T. Michael Seigler, Jesse B. Hoagg

Soft landing on small celestial bodies (SCBs) poses unique challenges, as gravitational models poorly characterize the higher-order gravitational effects of SCBs. Existing control approaches lack guarantees for safety under gravitational uncertainty. This paper proposes a three-stage control architecture that combines disturbance estimation, trajectory tracking, and safety enforcement. An extended high-gain observer estimates gravitational disturbances online, a feedback-linearizing controller tracks a reference trajectory, and a minimum-intervention quadratic program enforces state and input constraints while remaining close to the nominal control. The proposed approach enables aggressive yet safe maneuvers despite gravitational uncertainty. Numerical simulations demonstrate the effectiveness of the controller in achieving soft-landing on irregularly shaped SCBs, highlighting its potential for autonomous SCB missions.

Other0 citations2025-10-01arXiv ->

Predictive Control Barrier Functions for Discrete-Time Linear Systems with Unmodeled Delays

Juan Augusto Paredes Salazar, James Usevitch, Ankit Goel

This paper introduces a predictive control barrier function (PCBF) framework for enforcing state constraints in discrete-time systems with unknown relative degree, which can be caused by input delays or unmodeled input dynamics. Existing discrete-time CBF formulations typically require the construction of auxiliary barrier functions when the relative degree is greater than one, which complicates implementation and may yield conservative safe sets. The proposed PCBF framework addresses this challenge by extending the prediction horizon to construct a CBF for an associated system with relative degree one. As a result, the superlevel set of the PCBF coincides with the safe set, simplifying constraint enforcement and eliminating the need for auxiliary functions. The effectiveness of the proposed method is demonstrated on a discrete-time double integrator with input delay and a bicopter system with position constraints.

Theory0 citations2025-09-15arXiv ->

A Converse Control Lyapunov Theorem for Joint Safety and Stability

Thanin Quartz, Maxwell Fitzsimmons, Jun Liu

We show that the existence of a strictly compatible pair of control Lyapunov and control barrier functions is equivalent to the existence of a single smooth Lyapunov function that certifies both asymptotic stability and safety. This characterization complements existing literature on converse Lyapunov functions by establishing a partial differential equation (PDE) characterization with prescribed boundary conditions on the safe set, ensuring that the safe set is exactly certified by this Lyapunov function. The result also implies that if a safety and stability specification cannot be certified by a single Lyapunov function, then any pair of control Lyapunov and control barrier functions necessarily leads to a conflict and cannot be satisfied simultaneously in a robust sense.

Other0 citations2025-09-12arXiv ->

Combinatorial Control Barrier Functions: Nested Boolean and p-choose-r Compositions of Safety Constraints

Pio Ong, Haejoon Lee, Tamas G. Molnar, Dimitra Panagou, Aaron D. Ames

This paper investigates the problem of composing multiple control barrier functions (CBFs) -- and matrix control barrier functions (MCBFs) -- through logical and combinatorial operations. Standard CBF formulations naturally enable conjunctive (AND) combinations, but disjunctive (OR) and more general logical structures introduce nonsmoothness and possibly a combinatorial blow-up in the number of logical combinations. We introduce the framework of combinatorial CBFs that addresses p-choose-r safety specifications and their nested composition. The proposed framework ensures safety for the exact safe set in a scalable way, using the original number of primitive constraints. We establish theoretical guarantees on safety under these compositions, and we demonstrate their use on a patrolling problem in a multi-agent system.

Other Papers
MPC/Planning0 citations2026-06-29arXiv ->

Realtime Wind Estimation using Low Cost Quadrotor Uncrewed Aerial Vehicles

Hiranya Udagedara, Mahdis Bisheban

In environmental monitoring as well as emergency response applications such as wildfires, wind velocity measurement is essential. Quadrotor UAVs have become popular platforms for wind velocity estimation due to their maneuverability, compact size, and cost-effectiveness. Numerous studies use the Extended Kalman Filter (EKF) to estimate the wind velocity based on the quadrotor dynamic model. However, most of them use hovering quadrotors only for wind estimation, others use a near-linear trajectory to estimate near-constant velocities. Furthermore, EKF performance is constrained by its reliance on linearized approximations of the nonlinear quadrotor dynamics around current states, limiting accuracy in highly nonlinear scenarios, including windy conditions. This study proposes the use of an Unscented Kalman Filter (UKF), a nonlinear estimator to provide accurate wind estimations while maintaining the trajectory of the quadrotor UAV. The quadrotor is modeled on the Special Euclidean group SE(3) and the approach is evaluated through numerical simulations using a geometric controller to maintain quadrotor flight paths. The results indicate that as the nonlinearity of the simulation increases, the UKF consistently outperforms the EKF. This demonstrates the potential of the UKF as a reliable estimator for highly nonlinear scenarios, capable of maintaining the trajectory with minimal deviation while providing accurate wind velocity estimations.

Robotics0 citations2026-05-26arXiv ->

Bridging Control with Neural Network Verifier alpha-beta-CROWN: A Tutorial

Haoyu Li, Xiangru Zhong, Hao Cheng, Bin Hu, Huan Zhang

Learning-based methods for synthesizing controllers have gained popularity due to their high expressiveness and strong empirical performance. However, in safety-critical scenarios such as autonomous driving, robotics, and power systems, empirical performance alone is insufficient, and formal verification of controller properties such as stability and safety is highly desirable. Unfortunately, many prior verification approaches are either tied to specific structural assumptions on the system or the certificate, making them difficult to transfer across settings, or suffer from poor scalability on higher-dimensional neural network systems. In this tutorial, we present a unified framework that aims to mitigate this gap via bridging control with the state-of-the-art neural network verifier $α,\!β$-CROWN (alpha-beta-CROWN). At its core, $α,\!β$-CROWN is a general-purpose bounding engine for nonlinear functions represented as computation graphs: given an input domain, it can produce certified bounds and explicit linear relaxation of the nonlinear function. These certified bounds are useful on their own for tasks such as reachability analysis, and they also provide the foundation for more complex routines that perform satisfiability checking and optimization. More specifically, many control problems reduce to verifying real-valued inequalities over a state domain (e.g., Lyapunov theory). Consequently, $α,\!β$-CROWN enables scalable verification of such conditions by computing tight bounds and recursively partitioning and pruning subdomains based on the bounds. Thanks to GPU parallelization, this pipeline demonstrates superior scalability on verification and optimization problems that are challenging for traditional approaches. In this tutorial, we discuss the basics of $α,\!β$-CROWN and introduce its application to various control-related tasks.

Robotics0 citations2026-04-03arXiv ->

Redefining End-of-Life: Intelligent Automation for Electronics Remanufacturing Systems

Sibo Tian, Xiao Liang, Sara Behdad, Minghui Zheng

Remanufacturing is fundamentally more challenging than traditional manufacturing due to the significant uncertainty, variability, and incompleteness inherent in end-of-life (EoL) products. At the same time, it has become increasingly essential and urgent for facilitating a circular economy, driven by the growing volume of discarded electronic products and the escalating scarcity of critical materials. In this paper, we review the existing literature and examine the key challenges as well as emerging opportunities in intelligent automation for EoL electronics remanufacturing, providing a comprehensive overview of how robotics, control, and artificial intelligence (AI) can jointly enable scalable, safe, and intelligent remanufacturing systems. This paper starts with the definition, scope, and motivation of remanufacturing within the context of a circular economy, highlighting its societal and environmental significance. Then it delves into intelligent automation approaches for disassembly, inspection, sorting, and component reprocessing in this domain, covering advanced methods for multimodal perception, decision-making under uncertainty, flexible planning algorithms, and force-aware manipulation. The paper further reviews several emerging techniques, including large foundation models, human-in-the-loop integration, and digital twins that have the potential to support future research in this area. By integrating these topics, we aim to illustrate how next-generation remanufacturing systems can achieve robust, adaptable, and efficient operation in the face of complex real-world challenges.

Theory0 citations2026-03-24arXiv ->

Design Guidelines for Nonlinear Kalman Filters via Covariance Compensation

Shida Jiang, Jaewoong Lee, Shengyu Tao, Scott Moura

Nonlinear extensions of the Kalman filter (KF), such as the extended Kalman filter (EKF) and the unscented Kalman filter (UKF), are indispensable for state estimation in complex dynamical systems, yet the conditions for a nonlinear KF to provide robust and accurate estimations remain poorly understood. This work proposes a theoretical framework that identifies the causes of failure and success in certain nonlinear KFs and establishes guidelines for their improvement. Central to our framework is the concept of covariance compensation: the deviation between the covariance predicted by a nonlinear KF and that of the EKF. With this definition and detailed theoretical analysis, we derive three design guidelines for nonlinear KFs: (i) invariance under orthogonal transformations, (ii) sufficient covariance compensation beyond the EKF baseline, and (iii) selection of compensation magnitude that favors underconfidence. Both theoretical analysis and empirical validation confirm that adherence to these principles significantly improves estimation accuracy, whereas fixed parameter choices commonly adopted in the literature are often suboptimal. The codes and the proofs for all the theorems in this paper are available at https://github.com/Shida-Jiang/Guidelines-for-Nonlinear-Kalman-Filters.

Robotics0 citations2026-03-23arXiv ->

Partial Attention in Deep Reinforcement Learning for Safe Multi-Agent Control

Turki Bin Mohaya, Peter Seiler

Attention mechanisms excel at learning sequential patterns by discriminating data based on relevance and importance. This provides state-of-the-art performance in advanced generative artificial intelligence models. This paper applies this concept of an attention mechanism for multi-agent safe control. We specifically consider the design of a neural network to control autonomous vehicles in a highway merging scenario. The environment is modeled as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP). Within a QMIX framework, we include partial attention for each autonomous vehicle, thus allowing each ego vehicle to focus on the most relevant neighboring vehicles. Moreover, we propose a comprehensive reward signal that considers the global objectives of the environment (e.g., safety and vehicle flow) and the individual interests of each agent. Simulations are conducted in the Simulation of Urban Mobility (SUMO). The results show better performance compared to other driving algorithms in terms of safety, driving speed, and reward.

Robotics0 citations2026-03-15arXiv ->

Progress-Based Fault Detection and Health-Aware Task Allocation for Heterogeneous Multi-Robot Systems

Jack Cline, Christian Macaranas, Siavash Farzan

We present a progress-based fault detection module and its integration with dynamic task allocation for heterogeneous robot teams. The detector monitors a normalized task-completion signal with a lightweight Kalman filter (KF) and a normalized innovation squared (NIS) test, augmented with a low-rate stall gate, an uncertainty gate, and debounce logic. Health estimates influence the allocator via health-weighted costs and health-dependent masks; reallocation is event-triggered and regularized with an $\ell_1$ assignment-change penalty to limit reassignment churn while preserving feasibility through slack variables. The detector has constant per-robot update cost, and the allocation remains a convex quadratic program (QP). Experiments on a common team-task setup evaluate measurement-noise increases, velocity-slip biases, communication dropouts, and task abandonment. The results show timely detection in the noise and bias cases, maintained task completion with limited reassignment, and the expected observability delays under communication dropouts.

Robotics0 citations2026-03-10arXiv ->

A Generalized Voronoi Graph based Coverage Control Approach for Non-Convex Environment

Zuyi Guo, Ronghao Zheng, Meiqin Liu, Senlin Zhang

To address the challenge of efficient coverage by multi-robot systems in non-convex regions with multiple obstacles, this paper proposes a coverage control method based on the Generalized Voronoi Graph (GVG), which has two phases: Load-Balancing Algorithm phase and Collaborative Coverage phase. In Load-Balancing Algorithm phase, the non-convex region is partitioned into multiple sub-regions based on GVG. Besides, a weighted load-balancing algorithm is developed, which considers the quality differences among sub-regions. By iteratively optimizing the robot allocation ratio, the number of robots in each sub-region is matched with the sub-region quality to achieve load balance. In Collaborative Coverage phase, each robot is controlled by a new controller to effectively coverage the region. The convergence of the method is proved and its performance is evaluated through simulations.

Robotics0 citations2026-03-04arXiv ->

Gaussian Mixture-Based Inverse Perception Contract for Uncertainty-Aware Robot Navigation

Bingyao Du, Joonkyung Kim, Yiwei Lyu

Reliable navigation in cluttered environments requires perception outputs that are not only accurate but also equipped with uncertainty sets suitable for safe control. An inverse perception contract (IPC) provides such a connection by mapping perceptual estimates to sets that contain the ground truth with high confidence. Existing IPC formulations, however, instantiate uncertainty as a single ellipsoidal set and rely on deterministic trust scores to guide robot motion. Such a representation cannot capture the multi-modal and irregular structure of fine-grained perception errors, often resulting in over-conservative sets and degraded navigation performance. In this work, we introduce Gaussian Mixture-based Inverse Perception Contract (GM-IPC), which extends IPC to represent uncertainty with unions of ellipsoidal confidence sets derived from Gaussian mixture models. This design moves beyond deterministic single-set abstractions, enabling fine-grained, multi-modal, and non-convex error structures to be captured with formal guarantees. A learning framework is presented that trains GM-IPC to account for probabilistic inclusion, distribution matching, and empty-space penalties, ensuring both validity and compactness of the predicted sets. We further show that the resulting uncertainty characterizations can be leveraged in downstream planning frameworks for real-time safe navigation, enabling less conservative and more adaptive robot motion while preserving safety in a probabilistic manner.

RAL 2026 | 4 papers
CBF Related Papers
Robotics0 citations2026-07-22arXiv ->

Safe and Scalable Multi-Drone Payload Transport via CBF-based Reinforcement Learning with Zero-Shot Sim-to-Real Transfer

Jaeyoun Choi, Oswin So, Songyuan Zhang, Cooper Taylor, Chuchu Fan

Multi-drone payload transportation has emerged as a promising research paradigm with potential applications in construction, logistics, and disaster response. However, the complex coupled dynamics among drones, cables, and payloads pose significant challenges, and existing approaches remain limited in safety and scalability, particularly in dynamic and unstructured environments. In this work, we propose a learning-based framework for safe and scalable multi-drone cooperative payload transport. We introduce a minimal 2D abstraction that preserves the task-relevant drone-payload coupling required for coordination and safety, while remaining computationally efficient for large-scale learning. Using domain randomization over team size and physical parameters, we train a fully distributed policy via Discrete Graph Control Barrier Function Proximal Policy Optimization (DGPPO), enabling robust zero-shot sim-to-real transfer without fine-tuning. Extensive real-world evaluations demonstrate that a single learned policy generalizes across varying team sizes and task scenarios. Furthermore, multi-group hardware experiments show that the same policy can safely operate in dynamic environments, where other drone teams act as moving obstacles. These results indicate that the proposed framework enables efficient, safe, and scalable multi-drone payload transportation with strong generalization to complex real-world conditions.

Robotics0 citations2026-01-18arXiv ->

Allocating Corrective Control to Mitigate Multi-agent Safety Violations Under Private Preferences

Johnathan Corbin, Sarah H. Q. Li, Jonathan Rogers

We propose a novel framework that computes the corrective control efforts to ensure joint safety in multi-agent dynamical systems. This framework efficiently distributes the required corrective effort without revealing individual agents' private preferences. Our framework integrates high-order control barrier functions (HOCBFs), which enforce safety constraints with formal guarantees of safety for complex dynamical systems, with a privacy-preserving resource allocation mechanism based on the progressive second price (PSP) auction. When a joint safety constraint is violated, agents iteratively bid on new corrective efforts via 'avoidance credits' rather than explicitly solving for feasible corrective efforts that remove the safety violation. The resulting correction, determined via a second price payment rule, coincides with the socially optimal safe distribution of corrective actions. Critically, the bidding process achieves this optimal allocation efficiently and without revealing private preferences of individual agents. We demonstrate this method through multi-robot hardware experiments on the Robotarium platform.

Robotics0 citations2026-01-15arXiv ->

Proactive Local-Minima-Free Robot Navigation: Blending Motion Prediction with Safe Control

Yifan Xue, Ze Zhang, Knut Åkesson, Nadia Figueroa

This work addresses the challenge of safe and efficient mobile robot navigation in complex dynamic environments with concave moving obstacles. Reactive safe controllers like Control Barrier Functions (CBFs) design obstacle avoidance strategies based only on the current states of the obstacles, risking future collisions. To alleviate this problem, we use Gaussian processes to learn barrier functions online from multimodal motion predictions of obstacles generated by neural networks trained with energy-based learning. The learned barrier functions are then fed into quadratic programs using modulated CBFs (MCBFs), a local-minimum-free version of CBFs, to achieve safe and efficient navigation. The proposed framework makes two key contributions. First, it develops a prediction-to-barrier function online learning pipeline. Second, it introduces an autonomous parameter tuning algorithm that adapts MCBFs to deforming, prediction-based barrier functions. The framework is evaluated in both simulations and real-world experiments, consistently outperforming baselines and demonstrating superior safety and efficiency in crowded dynamic environments.

Other Papers
Robotics0 citations2026-06-15arXiv ->

LOPAL: Local Performance-Aware Active Learning from Imperfect Demonstrations

Johannes Heidersberger, Shail Jadav, Dongheui Lee

Learning from Demonstration (LfD) enables intuitive robot skill acquisition by allowing robots to learn directly from human task demonstrations. However, current methods often fail to address the fact that due to suboptimal and inconsistent human behavior, the quality of the demonstration can vary within each demonstration. Therefore, we introduce LOPAL (LOcal Performance-aware Active Learning), an active learning approach that leverages this local demonstration quality information. Our approach consists of two synergistic components. First, a local performance-driven LfD method uses a Gaussian Mixture Model (GMM) to encode both the demonstrated trajectories and their associated local quality assessments. This enables the generation of trajectories that outperform the imperfect demonstrations by utilizing complementary local data of high performance. Second, active data acquisition allows to improve beyond the imperfect demonstrations by collecting additional informative samples. In areas missing good data, the user is actively requested to provide corrections through a shared autonomy (SA) mechanism, while the robot autonomously executes the learned behavior. The efficacy of LOPAL was validated in both a simulation and a real-world experiment. The results from a real-world pipe inspection task showed that the proposed approach can achieve up to 27.31 % improvement in task performance while also reducing the effort required to collect the demonstrations.

RAL 2025 | 13 papers
CBF Related Papers
Robotics0 citations2025-11-29arXiv ->

Distributionally Robust Acceleration Control Barrier Filter for Efficient UAV Obstacle Avoidance

Dnyandeep Mandaokar, Bernhard Rinner

Dynamic obstacle avoidance (DOA) for unmanned aerial vehicles (UAVs) requires fast reaction under limited onboard resources. We introduce the distributionally robust acceleration control barrier function (DR-ACBF) as an efficient collision avoidance method maintaining safety regions. The method constructs a second-order control barrier function as linear half-space constraints on commanded acceleration. Latency, actuator limits, and obstacle accelerations are handled through an effective clearance that considers dynamics and delay. Uncertainty is mitigated using Cantelli tightening with per-obstacle risk. A DR-conditional value at risk (DR-CVaR)based early trigger expands margins near violations to improve DOA. Real-time execution is ensured via constant-time Gauss-Southwell projections. Simulation studies achieve similar avoidance performance at substantially lower computational effort than state-of-the-art baseline approaches. Experiments with Crazyflie drones demonstrate the feasibility of our approach.

MPC/Planning0 citations2025-11-24arXiv ->

Online Learning-Enhanced High Order Adaptive Safety Control

Lishuo Pan, Mattia Catellani, Thales C. Silva, Lorenzo Sabattini, Nora Ayanian

Control barrier functions (CBFs) are an effective model-based tool to formally certify the safety of a system. With the growing complexity of modern control problems, CBFs have received increasing attention in both optimization-based and learning-based control communities as a safety filter, owing to their provable guarantees. However, success in transferring these guarantees to real-world systems is critically tied to model accuracy. For example, payloads or wind disturbances can significantly influence the dynamics of an aerial vehicle and invalidate the safety guarantee. In this work, we propose an efficient yet flexible online learning-enhanced high-order adaptive control barrier function using Neural ODEs. Our approach improves the safety of a CBF controller on the fly, even under complex time-varying model perturbations. In particular, we deploy our hybrid adaptive CBF controller on a 38g nano quadrotor, keeping a safe distance from the obstacle, against 18km/h wind.

MPC/Planning0 citations2025-09-08arXiv ->

Safety Meets Speed: Accelerated Neural MPC with Safety Guarantees and No Retraining

Kaikai Wang, Tianxun Li, Liang Xu, Qinglei Hu, Keyou You

While Model Predictive Control (MPC) enforces safety via constraints, its real-time execution can exceed embedded compute budgets. We propose a Barrier-integrated Adaptive Neural Model Predictive Control (BAN-MPC) framework that synergizes neural networks' fast computation with MPC's constraint-handling capability. To ensure strict safety, we replace traditional Euclidean distance with Control Barrier Functions (CBFs) for collision avoidance. We integrate an offline-learned neural value function into the optimization objective of a Short-horizon MPC, substantially reducing online computational complexity. Additionally, we use a second neural network to learn the sensitivity of the value function to system parameters, and adaptively adjust the neural value function based on this neural sensitivity when model parameters change, eliminating the need for retraining and reducing offline computation costs. The hardware in-the-loop (HIL) experiments on Jetson Nano show that BAN-MPC solves 200 times faster than traditional MPC, enabling collision-free navigation with control error below 5\% under model parameter variations within 15\%, making it an effective embedded MPC alternative.

Other Papers
Robotics0 citations2026-06-10arXiv ->

Point Cloud Segmentation for Autonomous Clip Positioning in Laparoscopic Cholecystectomy on a Phantom

Balázs Gyenes, Nikolai Franke, Paul Maria Scheikl, Pit Henrich, Rayan Younis et al.

High-risk applications in robotics, such as robot-assisted surgery, present unique challenges. These systems must be both highly precise and interpretable in order to be deployed in environments with very low tolerance for error or unsafe exploration. We present the first robotic system to demonstrate autonomous clip positioning on a physical phantom in laparoscopic surgery, one of the most common interventions in general surgery. After segmentation of a colorless point cloud from a single camera, target positions for the clips are extracted using spline interpolation, and can then be adjusted by the human operator. The segmentation model is trained on only 60 hand-labeled real point clouds, reflecting data scarcity in the surgical domain. We overcome this with a combination of pre-training on 128,000 synthetic point clouds and two novel data augmentation techniques. The motion of the end-effector to each target is visualized for the operator, satisfying the unique motion constraints of minimally-invasive surgery while ensuring that the robot's actions are verifiable and interpretable. In real robot experiments, our system localizes targets with the required precision of 0.75mm at a 95% success rate and executes autonomous clip positioning with a 100% success rate. We provide insights that are applicable to many other surgical and non-surgical tasks that require identifying and navigating to a precise target. Source code and project page: https://github.com/balazsgyenes/kirurc

Robotics0 citations2025-10-28arXiv ->

VOCALoco: Viability-Optimized Cost-aware Adaptive Locomotion

Stanley Wu, Mohamad H. Danesh, Simon Li, Hanna Yurchyk, Amin Abyaneh et al.

Recent advancements in legged robot locomotion have facilitated traversal over increasingly complex terrains. Despite this progress, many existing approaches rely on end-to-end deep reinforcement learning (DRL), which poses limitations in terms of safety and interpretability, especially when generalizing to novel terrains. To overcome these challenges, we introduce VOCALoco, a modular skill-selection framework that dynamically adapts locomotion strategies based on perceptual input. Given a set of pre-trained locomotion policies, VOCALoco evaluates their viability and energy-consumption by predicting both the safety of execution and the anticipated cost of transport over a fixed planning horizon. This joint assessment enables the selection of policies that are both safe and energy-efficient, given the observed local terrain. We evaluate our approach on staircase locomotion tasks, demonstrating its performance in both simulated and real-world scenarios using a quadrupedal robot. Empirical results show that VOCALoco achieves improved robustness and safety during stair ascent and descent compared to a conventional end-to-end DRL policy

Robotics0 citations2025-06-22arXiv ->

GeNIE: A Generalizable Navigation System for In-the-Wild Environments

Jiaming Wang, Diwen Liu, Jizhuo Chen, Jiaxuan Da, Nuowen Qian et al.

Reliable navigation in unstructured, real-world environments remains a significant challenge for embodied agents, especially when operating across diverse terrains, weather conditions, and sensor configurations. In this paper, we introduce GeNIE (Generalizable Navigation System for In-the-Wild Environments), a robust navigation framework designed for global deployment. GeNIE integrates a generalizable traversability prediction model built on SAM2 with a novel path fusion strategy that enhances planning stability in noisy and ambiguous settings. We deployed GeNIE in the Earth Rover Challenge (ERC) at ICRA 2025, where it was evaluated across six countries spanning three continents. GeNIE took first place and achieved 79% of the maximum possible score, outperforming the second-best team by 17%, and completed the entire competition without a single human intervention. These results set a new benchmark for robust, generalizable outdoor robot navigation. We will release the codebase, pretrained model weights, and newly curated datasets to support future research in real-world navigation.

Robotics0 citations2025-04-27arXiv ->

LRFusionPR: A Polar BEV-Based LiDAR-Radar Fusion Network for Place Recognition

Zhangshuo Qi, Luqi Cheng, Zijie Zhou, Guangming Xiong

In autonomous driving, place recognition is critical for global localization in GPS-denied environments. LiDAR and radar-based place recognition methods have garnered increasing attention, as LiDAR provides precise ranging, whereas radar excels in adverse weather resilience. However, effectively leveraging LiDAR-radar fusion for place recognition remains challenging. The noisy and sparse nature of radar data limits its potential to further improve recognition accuracy. In addition, heterogeneous radar configurations complicate the development of unified cross-modality fusion frameworks. In this paper, we propose LRFusionPR, which improves recognition accuracy and robustness by fusing LiDAR with either single-chip or scanning radar. Technically, a dual-branch network is proposed to fuse different modalities within the unified polar coordinate bird's eye view (BEV) representation. In the fusion branch, cross-attention is utilized to perform cross-modality feature interactions. The knowledge from the fusion branch is simultaneously transferred to the distillation branch, which takes radar as its only input to further improve the robustness. Ultimately, the descriptors from both branches are concatenated, producing the multimodal global descriptor for place retrieval. Extensive evaluations on multiple datasets demonstrate that our LRFusionPR achieves accurate place recognition, while maintaining robustness under varying weather conditions. Our open-source code will be released at https://github.com/QiZS-BIT/LRFusionPR.

Robotics0 citations2025-04-20arXiv ->

ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion

Mingjie Zhang, Yuheng Du, Chengkai Wu, Jinni Zhou, Zhenchao Qi et al.

Navigating unknown environments to find a target object is a significant challenge. While semantic information is crucial for navigation, relying solely on it for decision-making may not always be efficient, especially in environments with weak semantic cues. Additionally, many methods are susceptible to misdetections, especially in environments with visually similar objects. To address these limitations, we propose ApexNav, a zero-shot object navigation framework that is both more efficient and reliable. For efficiency, ApexNav adaptively utilizes semantic information by analyzing its distribution in the environment, guiding exploration through semantic reasoning when cues are strong, and switching to geometry-based exploration when they are weak. For reliability, we propose a target-centric semantic fusion method that preserves long-term memory of the target and similar objects, enabling robust object identification even under noisy detections. We evaluate ApexNav on the HM3Dv1, HM3Dv2, and MP3D datasets, where it outperforms state-of-the-art methods in both SR and SPL metrics. Comprehensive ablation studies further demonstrate the effectiveness of each module. Furthermore, real-world experiments validate the practicality of ApexNav in physical environments. The code will be released at https://github.com/Robotics-STAR-Lab/ApexNav.

Robotics0 citations2025-03-07arXiv ->

Kaiwu: A Multimodal Manipulation Dataset and Framework for Robot Learning and Human-Robot Interaction

Shuo Jiang, Haonan Li, Ruochen Ren, Yanmin Zhou, Zhipeng Wang et al.

Cutting-edge robot learning techniques including foundation models and imitation learning from humans all pose huge demands on large-scale and high-quality datasets which constitute one of the bottleneck in the general intelligent robot fields. This paper presents the Kaiwu multimodal dataset to address the missing real-world synchronized multimodal data problems in the sophisticated assembling scenario,especially with dynamics information and its fine-grained labelling. The dataset first provides an integration of human,environment and robot data collection framework with 20 subjects and 30 interaction objects resulting in totally 11,664 instances of integrated actions. For each of the demonstration,hand motions,operation pressures,sounds of the assembling process,multi-view videos, high-precision motion capture information,eye gaze with first-person videos,electromyography signals are all recorded. Fine-grained multi-level annotation based on absolute timestamp,and semantic segmentation labelling are performed. Kaiwu dataset aims to facilitate robot learning,dexterous manipulation,human intention investigation and human-robot collaboration research.

Robotics0 citations2025-02-14arXiv ->

Diffusion Trajectory-guided Policy for Long-horizon Robot Manipulation

Shichao Fan, Quantao Yang, Yajie Liu, Kun Wu, Zhengping Che et al.

Recently, Vision-Language-Action models (VLA) have advanced robot imitation learning, but high data collection costs and limited demonstrations hinder generalization and current imitation learning methods struggle in out-of-distribution scenarios, especially for long-horizon tasks. A key challenge is how to mitigate compounding errors in imitation learning, which lead to cascading failures over extended trajectories. To address these challenges, we propose the Diffusion Trajectory-guided Policy (DTP) framework, which generates 2D trajectories through a diffusion model to guide policy learning for long-horizon tasks. By leveraging task-relevant trajectories, DTP provides trajectory-level guidance to reduce error accumulation. Our two-stage approach first trains a generative vision-language model to create diffusion-based trajectories, then refines the imitation policy using them. Experiments on the CALVIN benchmark show that DTP outperforms state-of-the-art baselines by 25% in success rate, starting from scratch without external pretraining. Moreover, DTP significantly improves real-world robot performance.

Robotics0 citations2024-10-25arXiv ->

Image-Based Visual Servoing for Enhanced Cooperation of Dual-Arm Manipulation

Zizhe Zhang, Yuan Yang, Wenqiang Zuo, Guangming Song, Aiguo Song et al.

The cooperation of a pair of robot manipulators is required to manipulate a target object without any fixtures. The conventional control methods coordinate the end-effector pose of each manipulator with that of the other using their kinematics and joint coordinate measurements. Yet, the manipulators' inaccurate kinematics and joint coordinate measurements can cause significant pose synchronization errors in practice. This paper thus proposes an image-based visual servoing approach for enhancing the cooperation of a dual-arm manipulation system. On top of the classical control, the visual servoing controller lets each manipulator use its carried camera to measure the image features of the other's marker and adapt its end-effector pose with the counterpart on the move. Because visual measurements are robust to kinematic errors, the proposed control can reduce the end-effector pose synchronization errors and the fluctuations of the interaction forces of the pair of manipulators on the move. Theoretical analyses have rigorously proven the stability of the closed-loop system. Comparative experiments on real robots have substantiated the effectiveness of the proposed control.

MPC/Planning0 citations2024-09-10arXiv ->

Kino-PAX: Highly Parallel Kinodynamic Sampling-based Planner

Nicolas Perrault, Qi Heng Ho, Morteza Lahijanian

Sampling-based motion planners (SBMPs) are effective for planning with complex kinodynamic constraints in high-dimensional spaces, but they still struggle to achieve real-time performance, which is mainly due to their serial computation design. We present Kinodynamic Parallel Accelerated eXpansion (Kino-PAX), a novel highly parallel kinodynamic SBMP designed for parallel devices such as GPUs. Kino-PAX grows a tree of trajectory segments directly in parallel. Our key insight is how to decompose the iterative tree growth process into three massively parallel subroutines. Kino-PAX is designed to align with the parallel device execution hierarchies, through ensuring that threads are largely independent, share equal workloads, and take advantage of low-latency resources while minimizing high-latency data transfers and process synchronization. This design results in a very efficient GPU implementation. We prove that Kino-PAX is probabilistically complete and analyze its scalability with compute hardware improvements. Empirical evaluations demonstrate solutions in the order of 10 ms on a desktop GPU and in the order of 100 ms on an embedded GPU, representing up to 1000 times improvement compared to coarse-grained CPU parallelization of state-of-the-art sequential algorithms over a range of complex environments and systems.

MPC/Planning0 citations2024-08-01arXiv ->

RESC: A Reinforcement Learning Based Search-to-Control Framework for Quadrotor Local Planning in Dense Environments

Zhaohong Liu, Wenxuan Gao, Yinshuai Sun, Peng Dong

Agile flight in complex environments poses significant challenges to current motion planning methods, as they often fail to fully leverage the quadrotor dynamic potential, leading to performance failures and reduced efficiency during aggressive maneuvers.Existing approaches frequently decouple trajectory optimization from control generation and neglect the dynamics, further limiting their ability to generate aggressive and feasible motions.To address these challenges, we introduce an enhanced Search-to-Control planning framework that integrates visibility path searching with reinforcement learning (RL) control generation, directly accounting for dynamics and bridging the gap between planning and control.Our method first extracts control points from collision-free paths using a proposed heuristic search, which are then refined by an RL policy to generate low-level control commands for the quadrotor controller, utilizing reduced-dimensional obstacle observations for efficient inference with lightweight neural networks.We validate the framework through simulations and real-world experiments, demonstrating improved time efficiency and dynamic maneuverability compared to existing methods, while confirming its robustness and applicability.

TAC 2025 | 2 papers
CBF Related Papers
MPC/Planning0 citations2025-09-26arXiv ->

Safe-by-Design: Approximate Nonlinear Model Predictive Control with Real Time Feasibility

Jan Olucak, Arthur Castello B. de Oliveira, Torbjørn Cunis

This paper establishes relationships between continuous-time, receding horizon, nonlinear model predictive control (MPC) and control Lyapunov and control barrier functions (CLF/CBF). We show that, if the cost function "behaves well" for points in the terminal set, then the optimal value function and the feasible set, respectively, define a compatible CLF/CBF pair on the MPC's region of attraction. We then proceed to prove that any approximation of the value function and the feasible set also define a CLF/CBF pair, as long as those approximations satisfy the same "well behavedness" condition; and that a feasible state feedback can be computed by solving an infinitesimal version of the MPC problem. This methodology permits the formulation of continuous-time small-sized quadratic programs for feedback and enables approximate solutions of the nonlinear model predictive controller with theoretical safety and convergence guarantee. Finally, we demonstrate the effectiveness of the proposed approach when compared to other constrained control techniques through numerical experiments for nonlinear constrained spacecraft control.

MPC/Planning0 citations2025-09-23arXiv ->

Verification and Synthesis of Discrete-Time Control Barrier Functions

Erfan Shakhesi, W. P. M. H. Heemels, Alexander Katriniok

Discrete-time Control Barrier Functions (DTCBFs) have recently attracted interest for guaranteeing safety and synthesizing safe controllers for discrete-time dynamical systems. This paper addresses the open challenges of verifying candidate DTCBFs and synthesizing DTCBFs for general nonlinear discrete-time systems with input constraints and arbitrary safe sets. In particular, we propose a branch-and-bound method, inspired by the $α$BB algorithm, for the verification of candidate DTCBFs in both cases, whether a corresponding control policy is known or unknown. We prove that this method, in a finite number of iterations, either verifies a given candidate function as a valid DTCBF or falsifies it by providing a counterexample (within predefined tolerances). As a second main contribution, we propose a novel bilevel optimization approach to synthesize a DTCBF and a corresponding control policy in finite time. This involves determining the unknown coefficients of a parameterized DTCBF and a parameterized control policy. Furthermore, we introduce various strategies to reduce the computational burden of the bilevel approach. We also demonstrate our methods using numerical case studies.